The α-expansion algorithm has had a significant impact in computer vision due to its generality, effectiveness, and speed. It is commonly used to minimize energies that involve unary, pairwise, and specialized higher-order terms. Our main algorithmic contribution is an extension of α-expansion that also optimizes "label costs" with wellcharacterized optimality bounds. Label costs penalize a solution based on the set of labels that appear in it, for example by simply penalizing the number of labels in the solution.Our energy has a natural interpretation as minimizing description length (MDL) and sheds light on classical algorithms like K-means and expectation-maximization (EM). Label costs are useful for multi-model fitting and we demonstrate several such applications: homography detection, motion segmentation, image segmentation, and compression. Our C++ and MATLAB code is publicly availableIn a labeling problem we are given a set of observations P (pixels, features, data points) and a finite set of labels L (categories, geometric models, disparities). The goal is to assign each observation p ∈ P a label f p ∈ L such that the joint labeling f minimizes some objective function E(f ).Most labeling problems in computer vision and machine learning are ill-posed and in need of regularization, but the most useful regularizers often make the problem NP-hard. Our work is about how to effectively optimize energies with two such regularizers: a preference for fewer unique labels in the solution (label costs), and a preference for spatial smoothness (smooth costs). Figures 1, 2, and 3 suggest how these criteria cooperate to give clean results. Fig. 1 Motion segmentation on the 1RT2RCR sequence (Tron and Vidal 2007). Energy (1) finds 3 dominant motions (a) but labels many points incorrectly. Energy (2) gives coherent segmentations (b) but finds redundant motions. Our energy combines the best of both (c)

No abstract

Person detection is a key problem for many computer vision tasks. While face detection has reached maturity, detecting people under a full variation of camera view-points, human poses, lighting conditions and occlusions is still a difficult challenge. In this work we focus on detecting human heads in natural scenes. Starting from the recent local R-CNN object detector, we extend it with two types of contextual cues. First, we leverage person-scene relations and propose a Global CNN model trained to predict positions and scales of heads directly from the full image. Second, we explicitly model pairwise relations among objects and train a Pairwise CNN model using a structured-output surrogate loss. The Local, Global and Pairwise models are combined into a joint CNN framework. To train and test our full model, we introduce a large dataset composed of 369, 846 human heads annotated in 224, 740 movie frames. We evaluate our method and demonstrate improvements of person head detection against several recent baselines in three datasets. We also show improvements of the detection speed provided by our model.

In this paper, we propose a novel application of Generative Adversarial Networks (GAN) to the synthesis of cells imaged by fluorescence microscopy. Compared to natural images, cells tend to have a simpler and more geometric global structure that facilitates image generation. However, the correlation between the spatial pattern of different fluorescent proteins reflects important biological functions, and synthesized images have to capture these relationships to be relevant for biological applications. We adapt GANs to the task at hand and propose new models with casual dependencies between image channels that can generate multichannel images, which would be impossible to obtain experimentally. We evaluate our approach using two independent techniques and compare it against sensible baselines. Finally, we demonstrate that by interpolating across the latent space we can mimic the known changes in protein localization that occur through time during the cell cycle, allowing us to predict temporal evolution from static images.