Consitent and Tractable Algorithms for Learning Markov Network Classifiers

Markov Network classifier is a generic model for structured output prediction which provides easy way to encode prior knowledge about label interactions. We propose Maximum-Margin based algorithms for learning MN classifier from examples given arbitrary graph of label interactions. Our work extends SOTA in two ways. First, we show how to efficiently learn MN from examples with missing labels by converting the problem into a convex optimization tractable by standard gradient methods. Second, we show how that the proposed learning algorithm is statistically consistent.

CMP Tomato Taste Comparison Challenge (TTCC)

The Tomato Taste Comparison Challenge evaluates the taste of tomato samples provided by researchers at Center for Machine Perception. One high-level motivation is to allow researchers to compare progress in the cultivation of delicious tomatoes over a span of several years. Another motivation is to compete for the glory of winning. No competition, no progress!


Hairstyle Transfer between Face Images

We propose a neural network which takes two inputs, a hair image and a face image, and produces an output image having the hair of the hair image seamlessly merged with the inner face of the face image. Our architecture consists of neural networks mapping the input images into a latent code of a pretrained StyleGAN2 which generates the output high-definition image. We propose an algorithm for training parameters of the architecture solely from synthetic images generated by the StyleGAN2 itself without the need of any annotations or external dataset of hairstyle images. We empirically demonstrate the effectiveness of our method in applications including hair-style transfer, hair generation for 3D morphable models, and hair-style interpolation. Fidelity of the generated images is verified by a user study and by a novel hairstyle metric proposed in the paper.


Optimal strategies for reject option classification

In classification with a reject option, the classifier is allowed in uncertain cases to abstain from prediction. The classical cost-based model of a reject option classifier requires the cost of rejection to be defined explicitly. Alternative bounded-improvement model and bounded-abstention model avoid the notion of reject cost. The bounded-improvement model seeks for a classifier with a guaranteed selective risk and maximal cover. The bounded-abstention model seeks for a classifier with the guaranteed cover and the minimal selective risk. We prove that despite their different formulations the three rejection models lead to the same prediction strategy: the Bayes classifier endowed with a randomized Bayes selection function. We define a notion of a proper uncertainty score as a scalar summary of prediction uncertainty which is sufficient to construct the randomized Bayes selection function. We propose Fisher consistent algorithm to learn the proper uncertainty score from examples for an arbitrary black-box classifier. We demonstrate the efficiency of the algorithm on different prediction problems including classification, ordinal regression and structured output classifier.


License Plate recognition and Super-resolution from Low-Resolution Videos

We developed CNN architecture recognizing license plates from a sequence of low-resolution videos. Our system works reliably on videos which are unreadable by humans. We also show how to a generate super-resolution LP images from low-res videos.


Learning CNNs from weakly annotated facial images

We show how to learn CNNs for face recognition using weakly annotated images where the annotation is assigned to a set of candidate faces rather than a single face like in the standard supervised setting. We use our method to create a database containing more than 300k faces of celebrities each annotated with his/her biological age, gender and identity.