We present an exploration of the rich theoretical connections between several classes of regularized models, network flows, and recent results in submodular function theory. This work unifies key aspects of these problems under a common theory, leading to novel methods for working with several important models of interest in statistics, machine learning and computer vision. In Part 1, we review the concepts of network flows and submodular function optimization theory foundational to our results. We then examine the connections between network flows and the minimum-norm algorithm from submodular optimization, extending and improving several current results. This leads to a concise representation of the structure of a large class of pairwise regularized models important in machine learning, statistics and computer vision. In Part 2, we describe the full regularization path of a class of penalized regression problems with dependent variables that includes the graph-guided LASSO and total variation constrained models. This description also motivates a practical algorithm. This allows us to efficiently find the regularization path of the discretized version of TV penalized models. Ultimately, our new algorithms scale up to high-dimensional problems with millions of variables.

Motivated by an important insight from neural science, we propose a new framework for understanding the success of the recently proposed "maxout" networks. The framework is based on encoding information on sparse pathways and recognizing the correct pathway at inference time. Elaborating further on this insight, we propose a novel deep network architecture, called "channel-out" network, which takes a much better advantage of sparse pathway encoding. In channel-out networks, pathways are not only formed a posteriori, but they are also actively selected according to the inference outputs from the lower layers. From a mathematical perspective, channel-out networks can represent a wider class of piece-wise continuous functions, thereby endowing the network with more expressive power than that of maxout networks. We test our channel-out networks on several well-known image classification benchmarks, setting new state-of-the-art performance on CIFAR-100 and STL-10, which represent some of the "harder" image classification benchmarks.

Conventional SVM-based image coding methods are founded on independently restricting the distortion in every image coefficient at some particular image representation. Geometrically, this implies allowing arbitrary signal distortions in an $n$-dimensional rectangle defined by the $\varepsilon$-insensitivity zone in each dimension of the selected image representation domain. Unfortunately, not every image representation domain is well-suited for such a simple, scalar-wise, approach because statistical and/or perceptual interactions between the coefficients may exist. These interactions imply that scalar approaches may induce distortions that do not follow the image statistics and/or are perceptually annoying. Taking into account these relations would imply using non-rectangular $\varepsilon$-insensitivity regions (allowing coupled distortions in different coefficients), which is beyond the conventional SVM formulation. In this paper, we report a condition on the suitable domain for developing efficient SVM image coding schemes. We analytically demonstrate that no linear domain fulfills this condition because of the statistical and perceptual inter-coefficient relations that exist in these domains. This theoretical result is experimentally confirmed by comparing SVM learning in previously reported linear domains and in a recently proposed non-linear perceptual domain that simultaneously reduces the statistical and perceptual relations (so it is closer to fulfilling the proposed condition). These results highlight the relevance of an appropriate choice of the image representation before SVM learning.

This paper presents two approaches for filter design based on stochastic distances for intensity speckle reduction. A window is defined around each pixel, overlapping samples are compared and only those which pass a goodness-of-fit test are used to compute the filtered value. The tests stem from stochastic divergences within the Information Theory framework. The technique is applied to intensity Synthetic Aperture Radar (SAR) data with homogeneous regions using the Gamma model. The first approach uses a Nagao-Matsuyama-type procedure for setting the overlapping samples, and the second uses the nonlocal method. The proposals are compared with the Improved Sigma filter and with anisotropic diffusion for speckled data (SRAD) using a protocol based on Monte Carlo simulation. Among the criteria used to quantify the quality of filters, we employ the equivalent number of looks, and line and edge preservation. Moreover, we also assessed the filters by the Universal Image Quality Index and by the Pearson correlation between edges. Applications to real images are also discussed. The proposed methods show good results.

Bag-of-Words approach has played an important role in recent works for image classification. In consideration of efficiency, most methods use k-means clustering to generate the codebook. The obtained codebooks often lose the cluster size and shape information with distortion errors and low discriminative power. Though some efforts have been made to optimize codebook in sparse coding, they usually incur higher computational cost. Moreover, they ignore the correlations between codes in the following coding stage, that leads to low discriminative power of the final representation. In this paper, we propose a bilevel visual words coding approach in consideration of representation ability, discriminative power and efficiency. In the bilevel codebook generation stage, k-means and an efficient spectral clustering are respectively run in each level by taking both class information and the shapes of each visual word cluster into account. To obtain discriminative representation in the coding stage, we design a certain localized coding rule with bilevel codebook to select local bases. To further achieve an efficient coding referring to this rule, an online method is proposed to efficiently learn a projection of local descriptor to the visual words in the codebook. After projection, coding can be efficiently completed by a low dimensional localized soft-assignment. Experimental results show that our proposed bilevel visual words coding approach outperforms the state-of-the-art approaches for image classification.

When considering the problem of unmixing hyperspectral images, most of the literature in the geoscience and image processing areas relies on the widely used linear mixing model (LMM). However, the LMM may be not valid and other nonlinear models need to be considered, for instance, when there are multi-scattering effects or intimate interactions. Consequently, over the last few years, several significant contributions have been proposed to overcome the limitations inherent in the LMM. In this paper, we present an overview of recent advances in nonlinear unmixing modeling.

Classic sparse representation for classification (SRC) method fails to incorporate the label information of training images, and meanwhile has a poor scalability due to the expensive computation for l_1 norm. In this paper, we propose a novel subspace sparse coding method with utilizing label information to effectively classify the images in the subspace. Our new approach unifies the tasks of dimension reduction and supervised sparse vector learning, by simultaneously preserving the data sparse structure and meanwhile seeking the optimal projection direction in the training stage, therefore accelerates the classification process in the test stage. Our method achieves both flat and structured sparsity for the vector representations, therefore making our framework more discriminative during the subspace learning and subsequent classification. The empirical results on 4 benchmark data sets demonstrate the effectiveness of our method.

This special issue of the AI Magazine is devoted to some exemplar works of AI on mobile devices. It includes four works that range from mobile activity recognition and air quality detection to machine translation and image compression.

Coming with the ever growing computational power of mobile devices, mobile visual search have undergone an evolution in techniques and applications. A significant trend is low bit rate visual search, where compact visual descriptors are extracted directly over a mobile and delivered as queries rather than raw images to reduce the query transmission latency. In this article, we introduce our work on low bit rate mobile landmark search, in which a compact yet discriminative landmark image descriptor is extracted by using location context such as GPS, crowd-sourced hotspot WLAN, and cell tower locations. The compactness originates from the bag-of-words image representation, with an offline learning from geotagged photos from online photo sharing websites including Flickr and Panoramio. The learning process involves segmenting the landmark photo collection by discrete geographical regions using Gaussian mixture model, and then boosting a ranking sensitive vocabulary within each region, with an “entropy” based descriptor compactness feedback to refine both phases iteratively. In online search, when entering a geographical region, the codebook in a mobile device are downstream adapted to generate extremely compact descriptors with promising discriminative ability. We have deployed landmark search apps to both HTC and iPhone mobile phones, working over the database of million scale images in typical areas like Beijing, New York, and Barcelona, and others. Our descriptor outperforms alternative compact descriptors (Chen et al. 2009; Chen et al., 2010; Chandrasekhar et al. 2009a; Chandrasekhar et al. 2009b) with significant margins. Beyond landmark search, this article will summarize the MPEG standarization progress of compact descriptor for visual search (CDVS) (Yuri et al. 2010; Yuri et al. 2011) towards application interoperability.

The idea of computer vision as the Bayesian inverse problem to computer graphics has a long history and an appealing elegance, but it has proved difficult to directly implement. Instead, most vision tasks are approached via complex bottom-up processing pipelines. Here we show that it is possible to write short, simple probabilistic graphics programs that define flexible generative models and to automatically invert them to interpret real-world images. Generative probabilistic graphics programs consist of a stochastic scene generator, a renderer based on graphics software, a stochastic likelihood model linking the renderer's output and the data, and latent variables that adjust the fidelity of the renderer and the tolerance of the likelihood model. Representations and algorithms from computer graphics, originally designed to produce high-quality images, are instead used as the deterministic backbone for highly approximate and stochastic generative models. This formulation combines probabilistic programming, computer graphics, and approximate Bayesian computation, and depends only on general-purpose, automatic inference techniques. We describe two applications: reading sequences of degraded and adversarially obscured alphanumeric characters, and inferring 3D road models from vehicle-mounted camera images. Each of the probabilistic graphics programs we present relies on under 20 lines of probabilistic code, and supports accurate, approximately Bayesian inferences about ambiguous real-world images.