Showing papers by "Stephen J. Maybank published in 2017"

Salient Object Detection via Structured Matrix Decomposition

Abstract: Low-rank recovery models have shown potential for salient object detection, where a matrix is decomposed into a low-rank matrix representing image background and a sparse matrix identifying salient objects. Two deficiencies, however, still exist. First, previous work typically assumes the elements in the sparse matrix are mutually independent, ignoring the spatial and pattern relations of image regions. Second, when the low-rank and sparse matrices are relatively coherent, e.g., when there are similarities between the salient objects and background or when the background is complicated, it is difficult for previous models to disentangle them. To address these problems, we propose a novel structured matrix decomposition model with two structural regularizations: (1) a tree-structured sparsity-inducing regularization that captures the image structure and enforces patches from the same object to have similar saliency values, and (2) a Laplacian regularization that enlarges the gaps between salient objects and the background in feature space. Furthermore, high-level priors are integrated to guide the matrix decomposition and boost the detection. We evaluate our model for salient object detection on five challenging datasets including single object, multiple objects and complex scene images, and show competitive results as compared with 24 state-of-the-art methods in terms of seven performance metrics.

Algorithm-Dependent Generalization Bounds for Multi-Task Learning

Abstract: Often, tasks are collected for multi-task learning (MTL) because they share similar feature structures. Based on this observation, in this paper, we present novel algorithm-dependent generalization bounds for MTL by exploiting the notion of algorithmic stability. We focus on the performance of one particular task and the average performance over multiple tasks by analyzing the generalization ability of a common parameter that is shared in MTL. When focusing on one particular task, with the help of a mild assumption on the feature structures, we interpret the function of the other tasks as a regularizer that produces a specific inductive bias. The algorithm for learning the common parameter, as well as the predictor, is thereby uniformly stable with respect to the domain of the particular task and has a generalization bound with a fast convergence rate of order $\mathcal {O}(1/n)$ , where $n$ is the sample size of the particular task. When focusing on the average performance over multiple tasks, we prove that a similar inductive bias exists under certain conditions on the feature structures. Thus, the corresponding algorithm for learning the common parameter is also uniformly stable with respect to the domains of the multiple tasks, and its generalization bound is of the order $\mathcal {O}(1/T)$ , where $T$ is the number of tasks. These theoretical analyses naturally show that the similarity of feature structures in MTL will lead to specific regularizations for predicting, which enables the learning algorithms to generalize fast and correctly from a few examples.

Hyperspectral Image Spectral-Spatial Feature Extraction via Tensor Principal Component Analysis

Abstract: We consider the tensor-based spectral-spatial feature extraction problem for hyperspectral image classification. First, a tensor framework based on circular convolution is proposed. Based on this framework, we extend the traditional principal component analysis (PCA) to its tensorial version tensor PCA (TPCA), which is applied to the spectral-spatial features of hyperspectral image data. The experiments show that the classification accuracy obtained using TPCA features is significantly higher than the accuracies obtained by its rivals.

Semi-Supervised Tensor-Based Graph Embedding Learning and Its Application to Visual Discriminant Tracking

Abstract: An appearance model adaptable to changes in object appearance is critical in visual object tracking. In this paper, we treat an image patch as a two-order tensor which preserves the original image structure. We design two graphs for characterizing the intrinsic local geometrical structure of the tensor samples of the object and the background. Graph embedding is used to reduce the dimensions of the tensors while preserving the structure of the graphs. Then, a discriminant embedding space is constructed. We prove two propositions for finding the transformation matrices which are used to map the original tensor samples to the tensor-based graph embedding space. In order to encode more discriminant information in the embedding space, we propose a transfer - learning- based semi-supervised strategy to iteratively adjust the embedding space into which discriminative information obtained from earlier times is transferred. We apply the proposed semi-supervised tensor-based graph embedding learning algorithm to visual tracking. The new tracking algorithm captures an object's appearance characteristics during tracking and uses a particle filter to estimate the optimal object state. Experimental results on the CVPR 2013 benchmark dataset demonstrate the effectiveness of the proposed tracking algorithm.

Spatio-Temporal Self-Organizing Map Deep Network for Dynamic Object Detection from Videos

Abstract: In dynamic object detection, it is challenging to construct an effective model to sufficiently characterize the spatial-temporal properties of the background. This paper proposes a new Spatio-Temporal Self-Organizing Map (STSOM) deep network to detect dynamic objects in complex scenarios. The proposed approach has several contributions: First, a novel STSOM shared by all pixels in a video frame is presented to efficiently model complex background. We exploit the fact that the motions of complex background have the global variation in the space and the local variation in the time, to train STSOM using the whole frames and the sequence of a pixel over time to tackle the variance of complex background. Second, a Bayesian parameter estimation based method is presented to learn thresholds automatically for all pixels to filter out the background. Last, in order to model the complex background more accurately, we extend the single-layer STSOM to the deep network. Then the background is filtered out layer by layer. Experimental results on CDnet 2014 dataset demonstrate that the proposed STSOM deep network outperforms numerous recently proposed methods in the overall performance and in most categories of scenarios.

Supervised classification via constrained subspace and tensor sparse representation

Abstract: SRC, a supervised classifier via sparse representation, has rapidly gained popularity in recent years and can be adapted to a wide range of applications based on the sparse solution of a linear system. First, we offer an intuitive geometric model called constrained subspace to explain the mechanism of SRC. The constrained subspace model connects the dots of NN, NFL, NS, NM. Then, inspired from the constrained subspace model, we extend SRC to its tensor-based variant, which takes as input samples of high-order tensors which are elements of an algebraic ring. A tensor sparse representation is used for query tensors. We verify in our experiments on several publicly available databases that the tensor-based SRC called tSRC outperforms traditional SRC in classification accuracy. Although demonstrated for image recognition, tSRC is easily adapted to other applications involving underdetermined linear systems.

GRMA: Generalized Range Move Algorithms for the Efficient Optimization of MRFs

Abstract: Markov random fields (MRF) have become an important tool for many vision applications, and the optimization of MRFs is a problem of fundamental importance. Recently, Veksler and Kumar et al. proposed the range move algorithms, which are some of the most successful optimizers. Instead of considering only two labels as in previous move-making algorithms, they explore a large search space over a range of labels in each iteration, and significantly outperform previous move-making algorithms. However, two problems have greatly limited the applicability of range move algorithms: (1) They are limited in the energy functions they can handle (i.e., only truncated convex functions); (2) They tend to be very slow compared to other move-making algorithms (e.g., $$\alpha $$ź-expansion and $$\alpha \beta $$źβ-swap). In this paper, we propose two generalized range move algorithms (GRMA) for the efficient optimization of MRFs. To address the first problem, we extend the GRMAs to more general energy functions by restricting the chosen labels in each move so that the energy function is submodular on the chosen subset. Furthermore, we provide a feasible sufficient condition for choosing these subsets of labels. To address the second problem, we dynamically obtain the iterative moves by solving set cover problems. This greatly reduces the number of moves during the optimization. We also propose a fast graph construction method for the GRMAs. Experiments show that the GRMAs offer a great speedup over previous range move algorithms, while yielding competitive solutions.