To improve robustness to significant mismatches between source domain and target domain - arising from changes such as illumination, pose and image quality - domain adaptation is increasingly popular in computer vision. But most of methods assume that the source data is from single domain, or that multi-domain datasets provide the domain label for training instances. In practice, most datasets are mixtures of multiple latent domains, and difficult to manually provide the domain label of each data point. In this paper, we propose a model that automatically discovers latent domains in visual datasets. We first assume the visual images are sampled from multiple manifolds, each of which represents different domain, and which are represented by different subspaces. Using the neighborhood structure estimated from images belonging to the same category, we approximate the local linear invariant subspace for each image based on its local structure, eliminating the category-specific elements of the feature. Based on the effectiveness of this representation, we then propose a squared-loss mutual information based clustering model with category distribution prior in each domain to infer the domain assignment for images. In experiment, we test our approach on two common image datasets, the results show that our method outperforms the existing state-of-the-art methods, and also show the superiority of multiple latent domain discovery.

We investigate weakly-supervised image parsing, i.e., assigning class labels to image regions by using image-level labels only. Existing studies pay main attention to the formulation of the weakly-supervised learning problem, i.e., how to propagate class labels from images to regions given an affinity graph of regions. Notably, however, the affinity graph of regions, which is generally constructed in relatively simpler settings in existing methods, is of crucial importance to the parsing performance due to the fact that the weakly-supervised parsing problem cannot be solved within a single image, and that the affinity graph enables label propagation among multiple images. In order to embed more semantics into the affinity graph, we propose novel criteria by exploiting the weak supervision information carefully, and develop two graphs: L1 semantic graph and k-NN semantic graph. Experimental results demonstrate that the proposed semantic graphs not only capture more semantic relevance, but also perform significantly better than conventional graphs in image parsing.

We present an algorithm for identity verification using only information from the hair. Face recognition in the wild (i.e., unconstrained settings) is highly useful in a variety of applications, but performance suffers due to many factors, e.g., obscured face, lighting variation, extreme pose angle, and expression. It is well known that humans utilize hair for identification under many of these scenarios due to either the consistent hair appearance of the same subject or obvious hair discrepancy of different subjects, but little work exists to replicate this intelligence artificially. We propose a learned hair matcher using shape, color, and texture features derived from localized patches through an AdaBoost technique with abstaining weak classifiers when features are not present in the given location. The proposed hair matcher achieves 71.53% accuracy on the LFW View 2 dataset. Hair also reduces the error of a Commercial Off-The-Shelf (COTS) face matcher through simple score-level fusion by 5.7%.

Low-rank coding (LRC), originated from matrix decomposition, is recently introduced into image classification. Following the standard bag-of-words (BOW) pipeline, when coding the data matrix in the sense of low-rankness incorporates contextual information into the traditional BOW model, this can capture the dependency relationship among neighbor patches. It differs from the traditional sparse coding paradigms which encode patches independently. Current LRC-based methods use l_1 norm to increase the discrimination and sparseness of the learned codes. However, such methods fail to consider the local manifold structure between dataspace and dictionary space. To solve this problem, we propose a locality-constrained low-rank coding (LCLR) algorithm for image representations. By using the geometric structure information as a regularization term,we can obtain more discriminative representations. In addition, we present a fast and stable online algorithmto solve the optimization problem. In the experiments,we evaluate LCLR with four benchmarks, including one face recognition dataset (extended Yale B), one handwrittendigit recognition dataset (USPS), and two image datasets (Scene13 for scene recognition and Caltech101 for object recognition). Experimental results show thatour approach outperforms many state-of-the-art algorithmseven with a linear classifier.

As robots become more ubiquitous, it is increasingly important for untrained users to be able to interact with them intuitively. In this work, we investigate how people refer to objects in the world during relatively unstructured communication with robots. We collect a corpus of deictic interactions from users describing objects, which we use to train language and gesture models that allow our robot to determine what objects are being indicated. We introduce a temporal extension to state-of-the-art hierarchical matching pursuit features to support gesture understanding, and demonstrate that combining multiple communication modalities more effectively captures user intent than relying on a single type of input. Finally, we present initial interactions with a robot that uses the learned models to follow commands while continuing to learn from user input.

We present a new Markov Chain Monte Carlo (MCMC) sampling algorithm for probabilistic programs. Our approach and tool, called R2, has the unique feature of employing program analysis in order to improve the efficiencyof MCMC sampling. Given an input program P, R2 propagates observations in P backwards to obtaina semantically equivalent program P' in which every probabilistic assignment is immediately followed by an observe statement. Inference is performed by a suitably modified version of the Metropolis-Hastings algorithm that exploits the structure of the program P'. This has the overall effect of preventing rejections due to program executions that fail to satisfy observations in P. We formalize the semantics of probabilistic programs and rigorously prove the correctness of R2. We also empirically demonstrate the effectiveness of R2—in particular, we show that R2 is able to produce results of similar quality as the CHURCH and STAN probabilistic programming tools with much shorter execution time.

One-class classification approaches have been proposed in the literature to learn classifiers from examples of only one class. But these approaches are not directly applicable to relational domains due to their reliance on a feature vector or a distance measure. We propose a non-parametric relational one-class classification approach based on first-order trees. We learn a tree-based distance measure that iteratively introduces new relational features to differentiate relational examples. We update the distance measure so as to maximize the one-class classification performance of our model. We also relate our model definition to existing work on probabilistic combination functions and density estimation. We experimentally show that our approach can discover relevant features and outperform three baseline approaches.

Sparse modeling has been highly successful in many real-world applications. While a lot of interests have been on convex regularization, recent studies show that nonconvexregularizers can outperform their convex counterparts in many situations.However, the resulting nonconvex optimization problems are often challenging, especiallyfor composite regularizers such as the nonconvex overlapping group lasso. In thispaper, byusing a recent mathematical tool known as the proximal average,we propose a novel proximal gradient descent method for optimization with a wide class of nonconvex and composite regularizers.Instead of directlysolving the proximal stepassociated with a composite regularizer, we average thesolutions from the proximal problems of the constituent regularizers. This simple strategy has guaranteed convergenceand low per-iteration complexity.Experimental results on a number of synthetic andreal-world data sets demonstrate the effectiveness and efficiency of theproposed optimization algorithm, and also the improved classification performanceresulting from thenonconvex regularizers.

We propose a voted dual averaging method for on- line classification problems with explicit regularization. This method employs the update rule of the regularized dual averaging (RDA) method proposed by Xiao, but only on the subsequence of training examples where a classification error is made. We derive a bound on the number of mistakes made by this method on the training set, as well as its generalization error rate. We also intro- duce the concept of relative strength of regularization, and show how it affects the mistake bound and gener- alization performance. We examine the method using l1-regularization on a large-scale natural language pro- cessing task, and obtained state-of-the-art classification performance with fairly sparse models.

Hashing is a popular approximate nearest neighbor search approach for large-scale image retrieval. Supervised hashing, which incorporates similarity/dissimilarity information on entity pairs to improve the quality of hashing function learning, has recently received increasing attention. However, in the existing supervised hashing methods for images, an input image is usually encoded by a vector of hand-crafted visual features. Such hand-crafted feature vectors do not necessarily preserve the accurate semantic similarities of images pairs, which may often degrade the performance of hashing function learning. In this paper, we propose a supervised hashing method for image retrieval, in which we automatically learn a good image representation tailored to hashing as well as a set of hash functions. The proposed method has two stages. In the first stage, given the pairwise similarity matrix $S$ over training images, we propose a scalable coordinate descent method to decompose $S$ into a product of $HH^T$ where $H$ is a matrix with each of its rows being the approximate hash code associated to a training image. In the second stage, we propose to simultaneously learn a good feature representation for the input images as well as a set of hash functions, via a deep convolutional network tailored to the learned hash codes in $H$ and optionally the discrete class labels of the images. Extensive empirical evaluations on three benchmark datasets with different kinds of images show that the proposed method has superior performance gains over several state-of-the-art supervised and unsupervised hashing methods.