Alexander Kolesnikov

Seed, Expand and Constrain: Three Principles for Weakly-Supervised Image Segmentation

We introduce a new loss function for the weakly-supervised training of semantic image segmentation models based on three guiding principles: to seed with weak localization cues, to expand objects based on the information about which classes can occur in an image, and to constrain the segmentations to coincide with object boundaries. We show experimentally that training a deep convolutional neural network using the proposed loss function leads to substantially better segmentations than previous state-of-the-art methods on the challenging PASCAL VOC 2012 dataset. We furthermore give insight into the working mechanism of our method by a detailed experimental study that illustrates how the segmentation quality is affected by each term of the proposed loss function as well as their combinations.

iCaRL: Incremental Classifier and Representation Learning

A major open problem on the road to artificial intelligence is the development of incrementally learning systems that learn about more and more concepts over time from a stream of data. In this work, we introduce a new training strategy, iCaRL, that allows learning in such a class-incremental way: only the training data for a small number of classes has to be present at the same time and new classes can be added progressively. iCaRL learns strong classifiers and a data representation simultaneously. This distinguishes it from earlier works that were fundamentally limited to fixed data representations and therefore incompatible with deep learning architectures. We show by experiments on CIFAR-100 and ImageNet ILSVRC 2012 data that iCaRL can learn many classes incrementally over a long period of time where other strategies quickly fail.

Closed-Form Approximate CRF Training for Scalable Image Segmentation

We present LS-CRF, a new method for training cyclic Conditional Random Fields (CRFs) from large datasets that is inspired by classical closed-form expressions for the maximum likelihood parameters of a generative graphical model with tree topology. Training a CRF with LS-CRF requires only solving a set of independent regression problems, each of which can be solved efficiently in closed form or by an iterative solver. This makes LS-CRF orders of magnitude faster than classical CRF training based on probabilistic inference, and at the same time more flexible and easier to implement than other approximate techniques, such as pseudolikelihood or piecewise training. We apply LS-CRF to the task of semantic image segmentation, showing that it achieves on par accuracy to other training techniques at higher speed, thereby allowing efficient CRF training from very large training sets. For example, training a linearly parameterized pairwise CRF on 150,000 images requires less than one hour on a modern workstation.

Improving Weakly-Supervised Object Localization By Micro-Annotation.

Weakly-supervised object localization methods tend to fail for object classes that consistently co-occur with the same background elements, e.g. trains on tracks. We propose a method to overcome these failures by adding a very small amount of model-specific additional annotation. The main idea is to cluster a deep networks mid-level representations and assign object or distractor labels to each cluster. Experiments show substantially improved localization results on the challenging ILSVC2014 dataset for bounding box detection and the PASCAL VOC2012 dataset for semantic segmentation.

Estimating Barriers to Gene Flow from Distorted Isolation by Distance Patterns

Ringbauer et al. introduce a novel method to estimate barriers to gene flow in a two-dimensional population. Their inference scheme utilizes geographically... In continuous populations with local migration, nearby pairs of individuals have on average more similar genotypes than geographically well-separated pairs. A barrier to gene flow distorts this classical pattern of isolation by distance. Genetic similarity is decreased for sample pairs on different sides of the barrier and increased for pairs on the same side near the barrier. Here, we introduce an inference scheme that uses this signal to detect and estimate the strength of a linear barrier to gene flow in two dimensions. We use a diffusion approximation to model the effects of a barrier on the geographic spread of ancestry backward in time. This approach allows us to calculate the chance of recent coalescence and probability of identity by descent. We introduce an inference scheme that fits these theoretical results to the geographic covariance structure of bialleleic genetic markers. It can estimate the strength of the barrier as well as several demographic parameters. We investigate the power of our inference scheme to detect barriers by applying it to a wide range of simulated data. We also showcase an example application to an Antirrhinum majus (snapdragon) flower-color hybrid zone, where we do not detect any signal of a strong genome-wide barrier to gene flow.