Making Visual Data a First-Class Citizen

“Above all, don't lie to yourself. The man who lies to himself and listens to his own lie comes to a point that he cannot distinguish the truth within him, or around him, and so loses all respect for himself and for others. And having no respect he ceases to love.” ― Fyodor Dostoyevsky, The Brothers Karamazov

City Forensics: Using Visual Elements to Predict Non-Visual City Attributes

To respect the power and beauty of machine learning algorithms, especially when they are applied to the visual world, let's take a look at three recent applications of learning-based "computer vision" to computer graphics. Researchers in computer graphics are known for producing truly captivating illustrations of their results, so this post is going to be very visual. Now is your chance to sit back and let the pictures do the talking.

Can you predict things simply by looking at street-view images?

Let's say you're going to visit an old-friend in a foreign country for the first time. You've never visited this country before and have no idea what kind of city/neighborhood your friend lives in. So you decide to get a sneak peak -- you enter your friend's address into Google Street View.

Most people can look at Google Street View images in a given location and estimate attributes such as "sketchy," "rural," "slum-like," "noisy" for the given neighborhood. TLDR; A person is a pretty good visual recommendation engine.

Can you predict if this looks like a safe location? 

(Screenshot of Street view for Manizales, Colombia on Google Earth)

Can a computer program predict things by looking at images? If so, then these kinds of computer programs could be used to automatically generate semantic map layovers (see the crime prediction overlay from the first figure), help organize fast-growing cities (computer vision meets urban planning?), and ultimately bring about a new generation of match-making "visual recommendation engines" (a whole suite of new startups).

Before I discuss the research paper behind this idea, here are two cool things you could do (in theory) with a non-visual data prediction algorithm. There are plenty of great product ideas in this space -- just be creative.

Startup Idea #1: Avoiding sketchy areas when traveling abroad 
A Personalized location recommendation engine could be used to find locations in a city that I might find interesting (techie coffee shop for entrepreneurs, a park good for frisbee) subject to my constraints (near my current location, in a low-danger area, low traffic).  Below is the kind of place you want to avoid if you're looking for a coffee and a place to open up your laptop to do some work.

Google Street Maps, Morumbi São Paulo: slum housing (image from geographyfieldwork.com)

Startup Idea #2: Apartment Pricing and Marketing from Images
Visual recommendation engines could be used to predict the best images to represent an apartment for an Airbnb listing.  It would be great if Airbnb had a filter that would let you upload videos of your apartment, and it would predict that set of static images that best depict your apartment to maximize earning potential. I'm sure that Airbnb users would pay extra for this feature if it was available for a small extra charge. The same computer vision prediction idea can be applied to home pricing on Zillow, Craigslist, and anywhere else that pictures of for-sale items are shared.

Google image search result for "Good looking apartment". Can computer vision be used to automatically select pictures that will make your apartment listing successful on Airbnb?

Part I. City Forensics: Using Visual Elements to Predict Non-Visual City Attributes

The Berkeley Computer Graphics Group has been working on predicting non-visual attributes from images, so before I describe their approach, let me discuss how Berkeley's Visual Elements relate to Deep Learning.

Predicting Chicago Thefts from San Francisco data. Predicting Philadelphia Housing Prices from Boston data. From City Forensics paper.

Deep Learning vs Mid-level Patch Discovery (Technical Discussion)
You might think that non-visual data prediction from images (if even possible) will require a deep understanding of the image and thus these approaches must be based on a recent ConvNet deep learning method. Obviously, knowing the locations and categories associated with each object in a scene could benefit any computer vision algorithm.  The problem is that such general purpose CNN recognition systems aren't powerful enough to parse Google Street View images, at least not yet.

Another extreme is to train classifiers on entire images.  This was initially done when researchers were using GIST, but there are just too many nuisance pixels inside a typical image, so it is better to focus your machine learning a subset of the image.  But how do you choose the subset of the image to focus on?

There exist computer vision algorithms that can mine a large dataset of images and automatically extract meaningful, repeatable, and detectable mid-level visual patterns. These methods are not label-based and work really well when there is an underlying theme tying together a collection of images. The set of all Google Street View Images from Paris satisfies this criterion.  Large collections of random images from the internet must be labeled before they can be used to produce the kind of stellar results we all expect out of deep learning. The Berkeley Group uses visual elements automatically mined from images as the core representation.  Mid-level visual patterns are simply chunks of the image which correspond to repeatable configurations -- they sometimes contain entire objects, parts of objects, and popular multiple object configurations. (See Figure below)  The mid-level visual patterns form a visual dictionary which can be used to represent the set of images. Different sets of images (e.g., images from two different US cities) will have different mid-level dictionaries. These dictionaries are similar to "Visual Words" but their creation uses more SVM-like machinery.

The patch mining algorithm is known as mid-level patch discovery. You can think of mid-level patch discovery as a visually intelligent K-means clustering algorithm, but for really really large datasets. Here's a figure from the ECCV 2012 paper which introduced mid-level discriminative patches.

Unsupervised Discovery of Mid-Level Discriminative Patches

Unsupervised Discovery of Mid-Level Discriminative Patches. Saurabh Singh, Abhinav Gupta and Alexei A. Efros. In European Conference on Computer Vision (2012).

I should also point out that non-final layers in a pre-trained CNN could also be used for representing images, without the need to use a descriptor such as HOG. I would expect the performance to improve, so the questions is perhaps: How long until somebody publishes an awesome unsupervised CNN-based patch discovery algorithm? I'm a handful of researchers are already working on it. :-)

Related Blog Post: From feature descriptors to deep learning: 20 years of computer vision

Related Blog Post: Deep Learning vs Machine Learning vs Pattern Recognition

The City Forensics paper from Berkeley tries to map the visual appearance of cities (as obtained from Google Street View Images) to non-visual data like crime statistics, housing prices and population density.  The basic idea is to 1.) mine discriminative patches from images and 2.) train a predictor which can map these visual primitives to non-visual data. While the underlying technique is that of mid-level patch discovery combined with Support Vector Regression (SVR), the result is an attribute-specific distribution over GPS coordinates.  Such a distribution should be appreciated for its own aesthetic value. I personally love custom data overlays.

City Forensics: Using Visual Elements to Predict Non-Visual City Attributes. Sean Arietta, Alexei A. Efros, Ravi Ramamoorthi, Maneesh Agrawala. In IEEE Transactions on Visualization and Computer Graphics (TVCG), 2014.

Part II. The Selfie 2.0: Computer Vision as a Sidekick

Sometimes you just want the algorithm to be your sidekick. Let's talk about a new and improved method for using vision algorithms and the wisdom of the crowds to select better pictures of your face. While you might think of an improved selfie as a silly application, you do want to look "professional" in your professional photos, sexy in your "selfies" and "friendly" in your family pictures. An algorithm that helps you get the desired picture is an algorithm the whole world can get behind.

Attractiveness versus Time. From MirrorMirror Paper.

The basic idea is to collect a large video of a single person which spans different emotions, times of day, different days, or whatever condition you would like to vary.  Given this video, you can use crowdsourcing to label frames based on a property like attractiveness or seriousness.  Given these labeled frames, you can then train a standard HOG detector and predict one of these attributes on new data. Below if a figure which shows the 10 best shots of the child (lots of smiling and eye contact) and the worst 10 shots (bad lighting, blur, red-eye, no eye contact).

10 good shots, 10 worst shots. From MirrorMirror Paper.

You can also collect a video of yourself as you go through a sequence of different emotions, get people to label frames, and build a system which can predict an attribute such as "seriousness".

Faces ranked from Most serious to least serious. From MirrorMirror Paper.

In this work, labeling was necessary for taking better selfies.  But if half of the world is taking pictures, while the other half is voting pictures up and down (or Tinder-style swiping left and right), then I think the data collection and data labeling effort won't be a big issue in years to come. Nevertheless, this is a cool way of scoring your photos. Regarding consumer applications, this is something that Google, Snapchat, and Facebook will probably integrate into their products very soon.

Mirror Mirror: Crowdsourcing Better Portraits. Jun-Yan Zhu, Aseem Agarwala, Alexei A. Efros, Eli Shechtman and Jue Wang. In ACM Transactions on Graphics (SIGGRAPH Asia), 2014.

Part III. What does it all mean? I'm ready for the cat pictures.

This final section revisits an old, simple, and powerful trick in computer vision and graphics. If you know how to compute the average of a sequence of numbers, then you'll have no problem understanding what an average image (or "mean image") is all about. And if you're read this far, don't worry, the cat picture is coming soon.

Computing average images (or "mean" images) is one of those tricks that I was introduced to very soon after I started working at CMU.  Antonio Torralba, who has always had "a few more visualization tricks" up his sleeve, started computing average images (in the early 2000s) to analyze scenes as well as datasets collected as part of the LabelMe project at MIT. There's really nothing more to the basic idea beyond simply averaging a bunch of pictures.

Teaser Image from AverageExplorer paper.

Usually this kind of averaging is done informally in research, to make some throwaway graphic, or make cool web-ready renderings.  It's great seeing an entire paper dedicated to a system which explores the concept of averaging even further. It took about 15 years of use until somebody was bold enough to write a paper about it. When you perform a little bit of alignment, the mean pictures look really awesome. Check out these cats!

Aligned cat images from the AverageExplorer paper. 

I want one! (Both the algorithm and a Platonic cat)

The AverageExplorer paper extends simple image average with some new tricks which make the operations much more effective. I won't say much about the paper (the link is below), just take at a peek at some of the coolest mean cats I've ever seen (visualized above) or a jaw-dropping way to look at community collected landmark photos (Oxford bridge mean image visualized below).

Aligned bridges from AverageExplorer paper. 

I wish Google would make all of Street View look like this.

AverageExplorer: Interactive Exploration and Alignment of Visual Data Collections. Jun-Yan Zhu, Yong Jae Lee, and Alexei A. Efros. In SIGGRAPH 2014.

Averaging images is a really powerful idea.  Want to know what your magical classifier is tuned to detect?  Compute the top detections and average them.  Soon enough you'll have a good idea of what's going on behind the scenes.

Conclusion

Allow me to mention the mastermind that helped bring most of these vision+graphics+learning applications to life.  There's an inimitable charm present in all of the works of Prof. Alyosha Efros -- a certain aesthetic that is missing from 2015's overly empirical zeitgeist.  He used to be at CMU, but recently moved back to Berkeley.

Being able to summarize several of years worth of research into a single computer generated graphic can go a long way to making your work memorable and inspirational. And maybe our lives don't need that much automation.  Maybe general purpose object recognition is too much? Maybe all we need is a little art? I want to leave you with a YouTube video from a recent 2015 lecture by Professor A.A. Efros titled "Making Visual Data a First-Class Citizen." If you want to hear the story in the master's own words, grab a drink and enjoy the lecture.

"Visual data is the biggest Big Data there is (Cisco projects that it will soon account for over 90% of internet traffic), but currently, the main way we can access it is via associated keywords. I will talk about some efforts towards indexing, retrieving, and mining visual data directly, without the use of keywords." ― A.A. Efros, Making Visual Data a First-Class Citizen

Deep Learning vs Probabilistic Graphical Models vs Logic

Today, let's take a look at three paradigms that have shaped the field of Artificial Intelligence in the last 50 years: Logic, Probabilistic Methods, and Deep Learning. The empirical, "data-driven", or big-data / deep-learning ideology triumphs today, but that wasn't always the case. Some of the earliest approaches to AI were based on Logic, and the transition from logic to data-driven methods has been heavily influenced by probabilistic thinking, something we will be investigating in this blog post.

Let's take a look back Logic and Probabilistic Graphical Models and make some predictions on where the field of AI and Machine Learning is likely to go in the near future. We will proceed in chronological order.

Image from Coursera's Probabilistic Graphical Models course

1. Logic and Algorithms (Common-sense "Thinking" Machines)

A lot of early work on Artificial Intelligence was concerned with Logic, Automated Theorem Proving, and manipulating symbols. It should not be a surprise that John McCarthy's seminal 1959 paper on AI had the title "Programs with common sense."

If we peek inside one of most popular AI textbooks, namely "Artificial Intelligence: A Modern Approach," we immediately notice that the beginning of the book is devoted to search, constraint satisfaction problems, first-order logic, and planning. The third edition's cover (pictured below) looks like a big chess board (because being good at chess used to be a sign of human intelligence), features a picture of Alan Turing (the father of computing theory) as well as a picture of Aristotle (one of the greatest classical philosophers which had quite a lot to say about intelligence).

The cover of AIMA, the canonical AI text for undergraduate CS students

Unfortunately, logic-based AI brushes the perception problem under the rug, and I've argued quite some time ago that understanding how perception works is really the key to unlocking the secrets of intelligence. Perception is one of those things which is easy for humans and immensely difficult for machines. (To read more see my 2011 blog post, Computer Vision is Artificial Intelligence). Logic is pure and traditional chess-playing bots are very algorithmic and search-y, but the real world is ugly, dirty, and ridden with uncertainty.

I think most contemporary AI researchers agree that Logic-based AI is dead. The kind of world where everything can be perfectly observed, a world with no measurement error, is not the world of robotics and big-data.  We live in the era of machine learning, and numerical techniques triumph over first-order logic.  As of 2015, I pity the fool who prefers Modus Ponens over Gradient Descent.

Logic is great for the classroom and I suspect that once enough perception problems become "essentially solved" that we will see a resurgence in Logic.  And while there will be plenty of open perception problems in the future, there will be scenarios where the community can stop worrying about perception and start revisiting these classical ideas. Perhaps in 2020.

Further reading: Logic and Artificial Intelligence from the Stanford Encyclopedia of Philosophy

2. Probability, Statistics, and Graphical Models ("Measuring" Machines)

Probabilistic methods in Artificial Intelligence came out of the need to deal with uncertainty. The middle part of the Artificial Intelligence a Modern Approach textbook is called "Uncertain Knowledge and Reasoning" and is a great introduction to these methods.  If you're picking up AIMA for the first time, I recommend you start with this section. And if you're a student starting out with AI, do yourself a favor and don't skimp on the math.

Intro to PDFs from Penn State's Probability Theory and Mathematical Statistics course

When most people think about probabilistic methods they think of counting.  In laymen's terms, it's fair to think of probabilistic methods as fancy counting methods.  Let's briefly take a look at what used to be the two competing methods for thinking probabilistically.

Frequentist methods are very empirical -- these methods are data-driven and make inferences purely from data.  Bayesian methods are more sophisticated and combine data-driven likelihoods with magical priors.  These priors often come from first principles or "intuitions" and the Bayesian approach is great for combining heuristics with data to make cleverer algorithms -- a nice mix of the rationalist and empiricist world views.

What is perhaps more exciting that then Frequentist vs. Bayesian flamewar is something known as Probabilistic Graphical Models.  This class of techniques comes from computer science, and even though Machine Learning is now a strong component of a CS and a Statistics degree, the true power of statistics only comes when it is married with computation.

Probabilistic Graphical Models are a marriage of Graph Theory with Probabilistic Methods and they were all the rage among Machine Learning researchers in the mid-2000s. Variational methods, Gibbs Sampling, and Belief Propagation were being pounded into the brains of CMU graduate students when I was in graduate school (2005-2011) and provided us with a superb mental framework for thinking about machine learning problems. I learned most of what I know about Graphical Models from Carlos Guestrin and Jonathan Huang. Carlos Guestrin is now the CEO of GraphLab, Inc (now known as Dato) which is a company that builds large-scale products for machine learning on graphs and Jonathan Huang is a senior research scientist at Google.

The video below is a high-level overview of GraphLab, but it serves a very nice overview of "graphical thinking" and how it fits into the modern data scientist's tool-belt. Carlos is an excellent lecturer and his presentation is less about the company's product and more about ways of thinking about next-generation machine learning systems.

A Computational Introduction to Probabilistic Graphical Models by GraphLab, Inc CEO Prof. Carlos Guestrin (Video Link updated 4/17/2018)
If you think that deep learning is going to solve all of your machine learning problems, you should really take a look at the above video.  If you're building recommender systems, an analytics platform for healthcare data, designing a new trading algorithm, or building the next generation search engine, Graphical Models are the perfect place to start.

Further reading:
Belief Propagation Algorithm Wikipedia Page
An Introduction to Variational Methods for Graphical Models by Michael Jordan et al.
Michael Jordan's webpage (one of the titans of inference and graphical models)

3. Deep Learning and Machine Learning (Data-Driven Machines)

Machine Learning is about learning from examples and today's state-of-the-art recognition techniques require a lot of training data, a deep neural network, and patience. Deep Learning emphasizes the network architecture of today's most successful machine learning approaches.  These methods are based on "deep" multi-layer neural networks with many hidden layers. NOTE: I'd like to emphasize that using deep architectures (as of 2015) is not new.  Just check out the following "deep" architecture from 1998.

LeNet-5 Figure From Yann LeCun's seminal "Gradient-based learning

applied to document recognition" paper.

When you take a look at modern guide about LeNet, it comes with the following disclaimer:

"To run this example on a GPU, you need a good GPU. It needs at least 1GB of GPU RAM. More may be required if your monitor is connected to the GPU.

When the GPU is connected to the monitor, there is a limit of a few seconds for each GPU function call. This is needed as current GPUs can’t be used for the monitor while performing computations. Without this limit, the screen would freeze for too long and make it look as if the computer froze. This example hits this limit with medium-quality GPUs. When the GPU isn’t connected to a monitor, there is no time limit. You can lower the batch size to fix the timeout problem."

It really makes me wonder how Yann was able to get anything out of his deep model back in 1998. Perhaps it's not surprising that it took another decade for the rest of us to get the memo.

UPDATE: Yann pointed out (via a Facebook comment) that the ConvNet work dates back to 1989. "It had about 400K connections and took about 3 weeks to train on the USPS dataset (8000 training examples) on a SUN4 machine." -- LeCun

A Deep Network from Yann's work at Bell Labs from 1989

NOTE: At roughly the same time (~1998) two crazy guys in California were trying to cache the entire internet inside the computers in their garage (they started some funny-sounding company which starts with a G). I don't know how they did it, but I guess sometimes to win big you have to do things that don't scale. Eventually, the world will catch up.

Further reading:
Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner. Gradient-based learning applied to document recognition. Proceedings of the IEEE, November 1998.

Y. LeCun, B. Boser, J. S. Denker, D. Henderson, R. E. Howard, W. Hubbard and L. D. Jackel: Backpropagation Applied to Handwritten Zip Code Recognition, Neural Computation, 1(4):541-551, Winter 1989

Deep Learning code: Modern LeNet implementation in Theano and docs.

Conclusion

I don't see traditional first-order logic making a comeback anytime soon. And while there is a lot of hype behind deep learning, distributed systems and "graphical thinking" is likely to make a much more profound impact on data science than heavily optimized CNNs. There is no reason why deep learning can't be combined with a GraphLab-style architecture, and some of the new exciting machine learning work in the next decade is likely to be a marriage of these two philosophies.

You can also check out a relevant post from last month:
Deep Learning vs Machine Learning vs Pattern Recognition

Discuss on Hacker News

Brand Spankin' New Vision Papers from ICCV 2013

The International Conference of Computer Vision, ICCV, gathers the world's best researchers in Computer Vision and Machine Learning to showcase their newest and hottest ideas. (My work on the Exemplar-SVM debuted two years ago at ICCV 2011 in Barcelona.) This year, at ICCV 2013 in Sydney, Australia, the vision community witnessed lots of grand new ideas, excellent presentations, and gained new insights which are likely to influence the direction of vision research in the upcoming decade.

3D data is everywhere.  Detectors are not only getting faster, but getting stylish.  Edges are making a comeback.  HOGgles let you see the world through the eyes of an algorithm. Computers can automatically make your face pictures more memorable. And why ever stop learning, when you can learn all day long?

Here is a breakdown of some of the must-read ICCV 2013 papers which I'd like to share with you:

---

From Large Scale Image Categorization to Entry-Level Categories, Vicente Ordonez, Jia Deng, Yejin Choi, Alexander C. Berg, Tamara L. Berg, ICCV 2013.

This paper is the Marr Prize winning paper from this year's conference.  It is all about entry-level categories - the labels people will use to name an object - which were originally defined and studied by psychologists in the 1980s. In the ICCV paper, the authors study entry-level categories at a large scale and learn the first models for predicting entry-level categories for images. The authors learn mappings between concepts predicted by existing visual recognition systems and entry-level concepts that could be useful for improving human-focused applications such as natural language image description or retrieval. NOTE: If you haven't read Eleanor Rosch's seminal 1978 paper, The Principles of Categorization, do yourself a favor: grab a tall coffee, read it and prepare to be rocked.

---

Structured Forests for Fast Edge Detection, P. Dollar and C. L. Zitnick, ICCV 2013.

This paper from Microsoft Research is all about pushing the boundaries for edge detection. Randomized Decision Trees and Forests have been used in lots of excellent Microsoft research papers, with Jamie Shotton's Kinect work being one of the best examples, and it is now being used for super high-speed edge detection.  However this paper is not just about edges.  Quoting the authors, "We describe a general purpose method for learning structured random decision forest that robustly uses structured labels to select splits in the trees."  Anybody serious about learning for low-level vision should take a look.

There is also some code available, but take a very detailed look at the license before you use it in your project.  It is not an MIT license.

---

HOGgles: Visualizing Object Detection Features, C. Vondrick, A. Khosla, T. Malisiewicz, A. Torralba. ICCV 2013.

"The real voyage of discovery consists not in seeking new landscapes but in having new eyes." — Marcel Proust

This is our MIT paper, which I already blogged about (Can you pass the HOGgles test?), so instead of rehashing what was already mentioned, I'll just leave you with the quote above.  There are lots of great visualizations that Carl Vondrick put together on the HOGgles project webpage, so take a look.

---

Style-aware Mid-level Representation for Discovering Visual Connections in Space and Time, Yong Jae Lee, Alexei A. Efros, and Martial Hebert, ICCV 2013.

“Learn how to see. Realize that everything connects to everything else.” – Leonardo da Vinci

This paper is all about discovering how visual entities change as a function of time and space.  One great example is how the appearance of cars has changed over the past several decades.  Another example is how typical Google Street View images change as a function of going North-to-South in the United States.  Surely the North looks different than the South -- we now have an algorithm that can automatically discover these precise differences.

By the way, congratulations on the move to Berkeley, Monsieur Efros.  I hope your insatiable thirst for cultured life will not only be satisfied in the city which fostered your intellectual growth, but you will continue to inspire, educate, and motivate the next generation of visionaries.

---

NEIL: Extracting Visual Knowledge from Web Data. Xinlei Chen, Abhinav Shrivastava and Abhinav Gupta. In ICCV 2013. www.neil-kb.com

Fucking awesome! I don't normally use profanity in my blog, but I couldn't come up with a better phrase to describe the ideas presented in this paper.  A computer program which runs 24/7 to collected visual data from the internet and continually learn what the world is all about.  This is machine learning, this is AI, this is the future.  None of this train on my favourite dataset, test on my favourite dataset bullshit.  If there's anybody that's going to do it the right way, its the CMU gang.  This paper gets my unofficial "Vision Award." Congratulations, Xinlei!

This sort of never-ending learning has been applied to text by Tom Mitchell's group (also from CMU), but this is the first, and serious, attempt at never-ending visual learning.  The underlying algorithm is a semi-supervised learning algorithm which uses Google Image search to bootstrap the initial detectors, but eventually learns object-object relationships, object-attribute relationships, and scene-attribute relationships.

---

Beyond Hard Negative Mining: Efficient Detector Learning via Block-Circulant Decomposition. J. F. Henriques, J. Carreira, R. Caseiro, J. Batista. ICCV 2013.

Want faster detectors? Tired of hard-negative mining? Love all things Fourier?  Then this paper is for you.  Aren't you now glad you fell in love with linear algebra at a young age? This paper very clearly shows that there is a better way to perform hard-negative mining when the negatives are mined from translations of an underlying image pattern, as is typically done in object detection.  The basic idea is simple, and that's why this paper wins the "thumbs-up from tombone" award. The crux of the derivation in the paper is the observation that the Gram matrix of a set of images and their translated versions, as modeled by cyclic shifts, exhibits a block-circulant structure.  Instead of incrementally mining negatives, in this paper they show that it is possible to learn directly from a training set comprising all image subwindows of a predetermined aspect-ratio and show this is feasible for a rich set of popular models including Ridge Regression, Support Vector Regression (SVR) and Logistic Regression.  Move over hard-negative mining, Joseph Fourier just rocked your world.

P.S. Joao Carreira also created the CPMC image segmentation algorithm at CVPR 2010.  A recent blog post from Piotr Dollár (December 10th, 2013), "A Seismic Shift in Object Detection" discusses how segmentation is coming back into vision in a big way.

---

3DNN: Viewpoint Invariant 3D Geometry Matching for Scene Understanding, Scott Satkin and Martial Hebert. ICCV 2013.

A new way of matching images that come equipped with 3D data.  Whether the data comes from Google Sketchup, or is the output of a Kinect-like scanner, more and more visual data comes with its own 3D interpretation.  Unfortunately, most state-of-the-art image matching methods rely on comparing purely visual cues.  This paper is based on an idea called "fine-grained geometry refinement" and allows the transfer of information across extreme viewpoint changes.  While still computationally expensive, it allows non-parametric (i.e., data-driven) approaches to get away with using significantly smaller amounts of data.

---

Modifying the Memorability of Face Photographs.  Aditya Khosla, Wilma A. Bainbridge, Antonio Torralba and Aude Oliva, ICCV 2013.

Ever wanted to look more memorable in your photos?  Maybe your ad-campaign could benefit from better face pictures which are more likely to stick in people's minds.  Well, now there's an algorithm for that.  Another great MIT paper, which the authors show that the memorability of photographs could not only be measured, but automatically enhanced!

---

SUN3D: A Database of Big Spaces Reconstructed using SfM and Object Labels. J. Xiao, A. Owens and A. Torralba. ICCV 2013. sun3d.cs.princeton.edu

Xiao et al, continue their hard-core data collection efforts.  Now in 3D.  In addition to collecting a vast dataset of 3D reconstructed scenes, they show that there are some kinds of errors that simply cannot be overcome with high-quality solvers.  Some problems are too big and too ambitious (e.g., walking around an entire house with a Kinect) for even the best industrial-grade solvers (Google's Ceres solver) to tackle.  In this paper, they show that a small amount of human annotation is all it takes to snap those reconstructions in place.  And not any sort of crazy, click-here, click-there interfaces.  Simple LabelMe-like annotation interfaces, which require annotating object polygons, can be used to create additional object-object constraints which help the solvers do their magic.  For anybody interested in long-range scene reconstruction, take a look at their paper.

If there's one person I've ever seen that collects data while the rest of the world sleeps, it is definitely Prof. Xiao.  Congratulations on the new faculty position!  Princeton has been starving for a person like you.  If anybody is looking for PhD/Masters/postdoc positions, and wants to work alongside one the most ambitious and driven upcoming researchers in vision (Prof. Xiao), take a look at his disclaimer/call for students/postdocs at Princeton, then apply to the program directly.  Did I mention that you probably have to be a hacker/scientist badass to land a position in his lab?

Other noteworthy papers:

Mining Multiple Queries for Image Retrieval: On-the-fly learning of an Object-specific Mid-level Representation. B. Fernando, T. Tuytelaars,  ICCV 2013.

Training Deformable Part Models with Decorrelated Features. R. Girshick, J. Malik, ICCV 2013.

Sorry if I missed your paper, there were just too many good ones to list.  For those of you still in Sydney, be sure to either take a picture of a Kangaroo, or eat one.

Why your vision lab needs a reading group

I have a certain attitude when it comes to computer vision research -- don't do it in isolation. Reading vision papers on your own is not enough.  Learning how your peers analyze computer vision ideas will only strengthen your own understanding of the field and help you become a more critical thinker.  And that is why at places like CMU and MIT we have computer vision reading groups.  The computer vision reading group at CMU (also known as MISC-read to the CMU vision hackers) has a long tradition, and Martial Hebert has made sure it is a strong part of the CMU vision culture.  Others ex-CMU hackers such as Sanjiv Kumar have continued the vision reading group tradition onto places such as Google Research in NY (correct me if this is no longer the case).  I have continued the reading group tradition to MIT (where I'm currently a postdoc) because I was surprised there wasn't one already!  In reality, we spend so much time talking about papers in an informal setting, that I felt it was a shame to not do so in a more organized fashion.

Image courtesy of Platypus

My personal philosophy is that as a vision researcher, the way towards the goal of creating novel long-lasting ideas is learning how others think about the field.  There's a lot of value in being able to analyze, criticize, and re-synthesize other researchers' ideas.  Believe me when I say that a lot of new vision papers come out of top tier vision conferences every year.  You should be reading them!  But not just reading, also criticizing them among your peers.  Because once you learn to criticize others' ideas, you will become better at promulgating your own.  Do not equate criticism with nasty words for the sake of being nasty -- good criticism stems from a keen understanding of what must be done in science to convince a broad audience of your ideas.

In case you want to start your own computer vision research group, I've collected some tips, tricks, and advice:

1. You don't need faculty.  If you can't find a season vision veteran to help you organize the event, do not worry.  You just need 3+ people interested in vision and the motivation to maintain weekly meetings.  Who cares if you don't understand every detail of every paper!  Nobody besides the authors will ever understand every detail.

2. Be fearless.  Ask dumb questions.  Alyosha Efros taught me that if you're reading a paper or listening to a presentation, if you don't understand something then there's a good chance you're not the only one in the audience with the same questions.  Sometimes younger PhD students are afraid of "asking a dumb question" in front of audience.  But if you love knowledge, then it is your duty to ask.  Silence will not get you far.  Be bold, be curious, and grow wise.  

3. Choose your own papers to present.  Do not present papers that others want you to present -- that is better left for a seminar course led by a faculty member.  In a reading group it is very important that you care about the problems you will be discussing with your peers.  If you keep up with this trend then when it comes to "paper writing time" you should be up to date on many relevant papers in your field and you will know about your other lab mates' research interests.

4. It is better to show a paper PDF up on a projector than cancel a meeting.  Even if everybody is busy, and the presenter didn't have time to create slides, it is important to keep the momentum going.

5. After a major conference, have all of the people who attended the conference present their "top K paper."  The week after CVPR it will be valuable to have such a massive vision brain dump onto your peers because it is unlikely that everybody got to attend. 

6. Book a room every week and try to have the meeting at the same time and place.  Have either the presenter or the reading group organizer send out an announcement with the paper they will be presenting ahead of time.  At MIT we share a google doc with the information about interesting papers and the upcoming presenter usually chooses the paper one week in advance so that the following week's presenter doesn't choose the same paper.  If somebody already presents your paper, don't do it a second time!  Choose another paper.  cvpapers.com is a great resource to find upcoming papers.

At CMU, there is a long rotating schedule which includes every vision student and faculty member.  Once it is your time to present, you can only get off the hook if you swap your slot with somebody else.  Being on a schedule months in advance means you'll have lots of time to prepare your slides.  At MIT, we are currently following the object recognition / scene understanding / object detection theme where we (Prof. Torralba, his students, his postdocs, his visiting students, etc) choose a paper highly relevant to our interests.  By keeping such a focus, we can really jump into the relevant details without having to explain fundamental concepts such as SVMs, features, etc.  However, at CMU the reading group is much broader because on the queue are students/profs interested in all aspects of vision and related fields such as graphics, illumination, geometry, learning, etc.

don't throw away old code: github-it!

My thesis experiments on Exemplar-SVMs (my PhD thesis link: Note, 33MB) would have taken approximately 20 CPU years to finish.  But not on a fat CMU cluster!  Here is some simple code which helped make things possible in ~1month of 200+ cores of crunching.  That scale of computation is not quite Google-scale computing, but it was a unforgettable experience as a CMU PhD student.  I've recently had to go back to the SSH / GNU Screen method of starting scripts at MIT, since we do not have torque/pbs there, but I definitely use these scripts.  Fork it, use it, change it, hack it, improve it, break it, learn from it, etc.

https://github.com/quantombone/warp_scripts

I used these scripts to drive the experiments in my Exemplar-SVM framework (also on Github).

The basic take home message is "do not throw away old code" which you found useful at some time.  C'mon ex-phd students, I know you wrote a lot of code, you graduated and now you feel embarrassed to share your code.  Who cares if you never had a chance to clean it up, if the world never gets to see it then it will die a silent death from lack of use.  Just put it on Github, and let others take a look.  Git is the world's best source control/versioning system. Its distributed nature makes it perfect for large-scale collaboration.  Now with github sharing is super easy! Sharing is caring.  Let's make the world a better place for hackerdom, one repository at a time.  I've met some great hackers at MIT, such as the great cvondrick, who is still teaching me how to branch like a champ.

Mathematicians share proofs.  Hackers share code.  Embrace technology, embrace Github.  If you ever want to hack with me, it is probably as important for you to know the basics of git as it is for you to be a master of linear algebra.

Additional Reading:

Distributed Version Control: The Future of History, an article about Git by some Kitware software engineers

CMU's Black Fridays: a graduating PhD student's perspective

I've always been amazed that the CMU department really knows what its PhD students are up to -- the big stuff as well as the little stuff.

Allow me to elaborate.  As a PhD student at CMU, you receive a sort of "report card" at the end of every semester during on what is known as "Black Friday." You first submit a short summary of your accomplishments and goals for next semester.  Then, on this special day, the professors talk to each other about their students (probably in some secret sound-proof discussion room).  While faculty are discussing our fates, we, the students do the opposite.  We relax, watch movies, play games, and *imagine* what our superiors are discussing.  Black Friday letters serve two roles, a role for the faculty, and a role for the students.

Image courtesy of diypapers

For the faculty, Black Friday is a way for the department to evaluate and monitor the progress of their PhD students.  Faculty members get a chance to discuss their students' hardships as well as their successes.  For the students, these letters are way to keep us in *check*.

"You better check yo self before you wreck yo self" - Ice Cube

The Black Friday letter lets us know explicitly what research qualifiers, writing qualifiers, etc they expect us to complete next semester.  They let us know if they are happy with our progress or unhappy.

Photo by Mattox

In practice, I found the letters to be a combination of "the good" and "the bad."  The good (a statement such as "we are happy that you got your paper accepted to ___") is like getting A's in grade school -- a yipee! moment.  The bad (a statement such as "we have noticed that you are struggling taking your experimental research to the next level, and feel that you are spending too much time on ___"), is what pushes us to experience those yipee! moments the following semester.  In the past, my Black Friday letters have included details regarding elements of my research and coursework that I didn't know any faculty member even knew about.  But the faculty care!  The students are the future, and there is nothing like critical feedback to help us achieve our goals.  There have been several times during my 6 years at CMU's Robotics Institute when my letter helped keep me in check.

I only wish there was a way for students to provide Black Friday letters to their faculty mentors...

Further reading:
Black Friday from Peter Lee
How do you evaluate your grad students? by Matt Welsh

CMU Robotics Instititue's vision finds a home at Google

Congratulations to PittPatt for their recent acquisition by Google.  PittPatt, a Pittsburgh-based startup, has its roots in CMU's Robotics Institute (where I'm currently a PhD student).  Henry Schneiderman, the CEO of PittPatt, did some truly hardcore computer vision work while doing his PhD under Takeo Kanade.

Two famous papers by Hendry Schneiderman and Takeo Kanade are the following:
H. Schneiderman, T. Kanade. "A Statistical Method for 3D Object Detection Applied to Faces and Cars". IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2000) pdf format


H. Schneiderman, T. Kanade. "Probabilistic Modeling of Local Appearance and Spatial Relationships for Object Recognition." IEEE Conference on Computer Vision and Pattern Recognition (CVPR 1998). pdf format


Here is what the front page of PittPatt states:

Joining Google is the next thrilling step in a journey that began with research at Carnegie Mellon University's Robotics Institute in the 1990s and continued with the launching of Pittsburgh Pattern Recognition (PittPatt) in 2004. We've worked hard to advance the research and technology in many important ways and have seen our technology come to life in some very interesting products. At Google, computer vision technology is already at the core of many existing products (such as Image Search, YouTube, Picasa, and Goggles), so it's a natural fit to join Google and bring the benefits of our research and technology to a wider audience. We will continue to tap the potential of computer vision in applications that range from simple photo organization to complex video and mobile applications.

We look forward to joining the team at Google!

The team at Pittsburgh Pattern Recognition

Perhaps Henry's success is yet another reason to come to CMU to get a vision PhD...

cvpr 2011: highlights from day 1

Today was the first main day of the CVPR 2011 conference.  Here are some papers which I found particularly exciting and a brief reason why they are super cool:

Becuase you can’t afford to miss this one:

Abhinav Gupta, Scott Satkin, Alexei A. Efros and Martial Hebert. From Scene Geometry to Human Workspace. In CVPR 2011.

Because large scale structure from motion meets graphical models:

David Crandall, Andrew Owens, Noah Snavely, and Dan Huttenlocher. Discrete-Continuous Optimization for Large-Scale Structure from Motion. In CVPR 2011.

Because segmentation provides a good basis for object discovery:

Galleguillos C., McFee B., Belongie S., Lanckriet G. From Region Similarity to Category Discovery. In CVPR 2011.

Because imitation provides a category-free way of understanding pose:

Graham Taylor, Ian Spiro, Christoph Bregler, and Rob Fergus. Learning Invarance through Imitation. In CVPR 2011. Project page (with links to supplementary material)

Because you don’t need to solve intractable graphical model inferences:

S. Ross, D. Munoz, M. Hebert, J. A. Bagnell. Learning Message-Passing Inference Machines for Structured Prediction.  In CVPR 2011.

Because a little bit of bottom-up never hurt a lot of top-down:

Thomas Brox, Lubomir Bourdev, Subhransu Maji, Jitendra Malik. Object Segmentation by Alignment of Poselet Activations to Image Contours. In CVPR 2011

Because you might want to perform segmentation simultaneously on several related images:

Sara Vicente, Carsten Rother and Vladimir Kolmogorov. Object Cosegmentation. In CVPR 2011.

I missed some of the posters later in the evening because I went for a short hike organized by Jianbo Shi (to Seven Falls).  After all, CVPR is in Colorado Springs, and it is silly to stay inside the conference the entire time.   Below is a pic of the falls (only a short drive from the CVPR11 conference hotel). 

After several hours of talks it was good to get some fresh air and see some waterfalls in Colorado Springs!  On Friday, I'm going on the Pikes Beak downhill bike ride with some friends and it should be super-fun.

Beyond pixel-wise labeling: Blocks World Revisited

"Thoughts without content are empty, intuitions without concepts are blind." -- Immanuel Kant 

The Holy Grail problem of computer vision research is general-purpose image understanding.  Given as input a digital image (perhaps from Flickr or from Google Image search), we want to recognize the depicted objects (cars, dogs, sheep, Macbook Pros), their functional properties (which of the depicted objects are suitable for sitting), and recover the underlying geometry and spatial relations (which objects are lying on the desk). 

The early days of vision were dominated via the "Image Understanding as Inverse Optics" mentality.  In order to make the problem easier, as well as to cope with the meager computational resources of the 60s, early computer vision researchers tried to recover the 3D geometry of simple scenes consisting of arrangements of blocks.  One of the earlier efforts in this direction, is the PhD thesis Machine Perception of Three-Dimensional Solids by Larry Roberts from MIT back in 1963.

But wait -- these block-worlds are unlike anything found in the real world!  The drastic divide between the imagery that vision researchers were studying in the 60s and what humans observe during their daily experiences ultimately led to the disappearance of block-worlds in computer vision research.

Image Parsing Concept Image from Computer Blindness Blog

Over the past couple of decades, we have seen the success of Machine Learning, and it is of no surprise that we are currently living in the "Image Understanding as statistical inference" era.  While a single 256x256 grayscale image might have been okay to use in the 1960s, today's computer vision researchers use powerful computer clusters and do serious heavy-lifting on millions of real-world megapixel images.  The man-made blocks-world of the 1960s is a thing of the past, and the variety found on random images downloaded from Flickr is the complexity we must now cope with.

---

While the style of computer vision research has shifted since its early days in the 1960s/1970s,  many old ideas (and perhaps prematurely considered outdated) are making a comeback!

Assigning basic-level object category labels to pixels is a very popular theme in vision.  Unfortunately, to gain a deeper understanding of an image, robots will inevitably have to go beyond pixel-level class labels.  (This is one of the central themes in my thesis -- coming out soon!)  Given human-level understanding of a scene, it is trivial to represent it as a pixel-wise labeling map, but given a pixel-wise labeling map it is not trivial to convert it to human-level understanding. 

What sort of questions can be answered about a scene when the output of an "image understanding" system is represented as a pixel-wise label map?

1. Is there a car in the image?
2. Is there a person at this location in the image?

What questions cannot be answered given a pixel-wise label map?

1. How many cars are in this image? (While there are some approaches that strive to deal with delineating object instance boundaries, most image parsing approaches fail to recognize boundaries between two instances of the same category)
2. Which surfaces can I sit on?
3. Where can I park my car?
4. How geometrically stable are the objects in the scene?


While I have more criticisms than tentative solutions, I believe that vision students shouldn't be parochially preoccupied with solely the most recent approach to image understanding.  It is valuable to go back several decades in the literature and gain a broader perspective on image understanding.  However, some progress is being made!  A deeply insightful upcoming paper from ECCV 2010, is the following:

Abhinav Gupta, Alexei A. Efros and Martial Hebert, Blocks World Revisited: Image Understanding Using Qualitative Geometry and Mechanics, European Conference on Computer Vision, 2010. (PDF)

What Abhinav Gupta does very elegantly in this paper is connect the blocks-world research of the 1960s with the geometric-class estimation problem, as introduced by Derek Hoiem.  While the final system is evaluation in a Hoiem-like pixel-wise labeling task, the actual scene representation is 3D.  The blocks in this approach are more abstract than the Lego-like volumes in the 1960s -- Abhinav's blocks are actually cars, buildings, and trees. I included the infamous Immanuel Kant quote, because I feel it describes Abhinav's work very well.  Abhinav introduces the block as a theoretical construct which glues together a scene's elements and provides a much more solid interpretation -- Abhinav's blocks add the content to geometric image understanding which is lacking in the purely pixe-wise approaches.

While integrating large-scale categorization into this type of geometric reasoning is still an open problem, Abhinav provides us visionaries with a glimpse of what image understanding should be.  The integration of robotics with image understanding technology will surely drive pixel-based "dumb" image understanding approaches to extinction.