Sparse approximation

About: Sparse approximation is a research topic. Over the lifetime, 18037 publications have been published within this topic receiving 497739 citations. The topic is also known as: Sparse approximation.

Group Sparse Coding

Abstract: Bag-of-words document representations are often used in text, image and video processing. While it is relatively easy to determine a suitable word dictionary for text documents, there is no simple mapping from raw images or videos to dictionary terms. The classical approach builds a dictionary using vector quantization over a large set of useful visual descriptors extracted from a training set, and uses a nearest-neighbor algorithm to count the number of occurrences of each dictionary word in documents to be encoded. More robust approaches have been proposed recently that represent each visual descriptor as a sparse weighted combination of dictionary words. While favoring a sparse representation at the level of visual descriptors, those methods however do not ensure that images have sparse representation. In this work, we use mixed-norm regularization to achieve sparsity at the image level as well as a small overall dictionary. This approach can also be used to encourage using the same dictionary words for all the images in a class, providing a discriminative signal in the construction of image representations. Experimental results on a benchmark image classification dataset show that when compact image or dictionary representations are needed for computational efficiency, the proposed approach yields better mean average precision in classification.

Transferred Deep Learning for Anomaly Detection in Hyperspectral Imagery

Abstract: In this letter, a novel anomaly detection framework with transferred deep convolutional neural network (CNN) is proposed. The framework is designed by considering the following facts: 1) a reference data with labeled samples are utilized, because no prior information is available about the image scene for anomaly detection and 2) pixel pairs are generated to enlarge the sample size, since the advantage of CNN can be realized only if the number of training samples is sufficient. A multilayer CNN is trained by using difference between pixel pairs generated from the reference image scene. Then, for each pixel in the image for anomaly detection, difference between pixel pairs, constructed by combining the center pixel and its surrounding pixels, is classified by the trained CNN with the result of similarity measurement. The detection output is simply generated by averaging these similarity scores. Experimental performance demonstrates that the proposed algorithm outperforms the classic Reed-Xiaoli and the state-of-the-art representation-based detectors, such as sparse representation-based detector (SRD) and collaborative representation-based detector.

Are sparse representations really relevant for image classification

Abstract: Recent years have seen an increasing interest in sparse representations for image classification and object recognition, probably motivated by evidence from the analysis of the primate visual cortex. It is still unclear, however, whether or not sparsity helps classification. In this paper we evaluate its impact on the recognition rate using a shallow modular architecture, adopting both standard filter banks and filter banks learned in an unsupervised way. In our experiments on the CIFAR-IO and on the Caltech-101 datasets, enforcing sparsity constraints actually does not improve recognition performance. This has an important practical impact in image descriptor design, as enforcing these constraints can have a heavy computational cost.

Partial Person Re-Identification

Abstract: We address a new partial person re-identification (re-id) problem, where only a partial observation of a person is available for matching across different non-overlapping camera views. This differs significantly from the conventional person re-id setting where it is assumed that the full body of a person is detected and aligned. To solve this more challenging and realistic re-id problem without the implicit assumption of manual body-parts alignment, we propose a matching framework consisting of 1) a local patch-level matching model based on a novel sparse representation classification formulation with explicit patch ambiguity modelling, and 2) a global part-based matching model providing complementary spatial layout information. Our framework is evaluated on a new partial person re-id dataset as well as two existing datasets modified to include partial person images. The results show that the proposed method outperforms significantly existing re-id methods as well as other partial visual matching methods.

Efficient Compressive Sensing with Deterministic Guarantees Using Expander Graphs

Abstract: Compressive sensing is an emerging technology which can recover a sparse signal vector of dimension n via a much smaller number of measurements than n. However, the existing compressive sensing methods may still suffer from relatively high recovery complexity, such as O(n3), or can only work efficiently when the signal is super sparse, sometimes without deterministic performance guarantees. In this paper, we propose a compressive sensing scheme with deterministic performance guarantees using expander-graphs-based measurement matrices and show that the signal recovery can be achieved with complexity O(n) even if the number of nonzero elements k grows linearly with n. We also investigate compressive sensing for approximately sparse signals using this new method. Moreover, explicit constructions of the considered expander graphs exist. Simulation results are given to show the performance and complexity of the new method.