Discriminative Local Sparse Representation by Robust Adaptive Dictionary Pair Learning

Sun, Yulin; Zhang, Zhao; Jiang, Weizhong; Zhang, Zheng; Zhang, Li; Yan, Shuicheng; Wang, Meng

doi:10.1109/tnnls.2019.2954545

Cited by 62 publications

(28 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are other solutions, for example, Yulin Sun et al, propose a structured Robust Adaptive Dictionary Pair Learning(RA-DPL)framework for the discriminative sparse representation learning. To achieve powerful representation ability of the available samples, the setting of RA-DPL seamlessly integrates the robust projective dictionary pair learning, locality-adaptive sparse representation and discriminative coding coefficients learning into a unified learning framework [45].…”

Section: ) Handle Small and Dense Noisementioning

confidence: 99%

Identification of Underwater Targets Based on Sparse Representation

2020

IEEE Access

View full text Add to dashboard Cite

We consider using sparse representations to identify underwater targets, since underwater acoustic signal have sparse characteristics. We consider the identification problem as one of the identifying among multiple linear regression models and believe that the new theory from sparse signal representation provides the key to solving this problem. Based on a sparse representation computed by 1 − minimization, we propose a general classification algorithm for (hydroacoustic signal-based) targets identification. This new framework provides new insights into identifying two key issues in underwater targets: feature extraction and robustness of signal loss and noise interference. For feature extraction, we point out that feature extraction is no longer critical if the sparseness of the underwater acoustic signal is properly utilized. The critical is whether the number of features is large enough and whether the sparse representation is correctly computed. This framework can handle errors due to signal loss and noise interference uniformly by exploiting the fact that these errors are often sparse with respect to the standard (hydroacoustic signal) basis. Extensive experiments have been conducted based on a public underwater acoustic signal sampling set to verify the efficacy of the proposed algorithm and corroborate the above claims. INDEX TERMS Identification of underwater targets, sparse representation, 1 − norm, compressed sensing.

show abstract

Section: ) Handle Small and Dense Noisementioning

confidence: 99%

Identification of Underwater Targets Based on Sparse Representation

2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…F is the Frobenius norm, f (S) is function on S and q is the sparsity measure. The second type of dictionary learns several class-specific sub-dictionaries so that data can be better represented in their corresponding sub-dictionary than others [45]- [49]. This type of approach helps to capture those discriminative components that enhance the interclass diversities.…”

Section: A Dictionary Learningmentioning

confidence: 99%

“…In [48], the discriminative Fisher embedding dictionary is proposed that tries to enhance the interclass variability and minimizes the intraclass variability. An adaptive dictionary pair learning framework is proposed to improve the discriminative ability of derived sparse codes [49]. The objective function for learning such dictionary can be defined as…”

Section: A Dictionary Learningmentioning

confidence: 99%

Genetic Algorithm Optimized Structured Dictionary for Discriminative Block Sparse Representation

Kumar

Sinha

2020

IEEE Access

View full text Add to dashboard Cite

This paper presents a few innovations towards learning a discriminative block-structured dictionary. The learning process of such a dictionary is broadly divided into two steps: block formation and dictionary update. In the existing works on block structure estimation, it is assumed that the maximum block size is known a priori. In real-world problems, such an assumption may be sub-optimal. For addressing that, a genetic algorithm optimized K-means clustering based block formation approach is proposed in this work. We also propose a novel dictionary learning approach that incorporates three attributes, namely, reconstruction and discriminative fidelities, block-wise incoherence, and 2,1-norm regularization. To further enhance the discriminative ability of the sparse codes, the class-specific and class-common information are modeled separately in the dictionary. The 2,1-norm regularization enhances the consistency among sparse codes belonging to the same-class data. In the proposed approach, the dictionary is updated block-wise by employing the singular value decomposition of the composite error matrix obtained through the weighted combination of the component errors. The proposed innovations are evaluated on several public image databases for super-resolution and classification tasks. Along with those image databases, speech based speaker verification task is also evaluated the proposed approach in a few different domains to validate the generalizability. The experimental results obtained on these different databases demonstrate the effectiveness of the proposed approaches when compared with the respective state-of-the-art.

show abstract

“…ITH the increasing complexity of contents, diversity of distribution and high-dimensionality of real data, how to represent data efficiently for subsequent classification or clustering still remains an important research topic [1][2][3][9] [50]. To represent data, some feasible methods can be used, such as sparse representation (SR) by dictionary learning (DL) [4][5][6][7][8], low-rank coding [9][10][15] [38][39] and matrix factorization [11] [12], which are inspired by the fact that high-dimensional data can usually be characterized by applying a low-dimensional or compressed space in which the possible noise and redundant information can be removed in addition to preserving the useful information and important structures.…”

Section: Introductionmentioning

confidence: 99%

“…Although DPL and ADDL aim to address this issue by calculating a synthesis dictionary jointly, they both did not consider regularizing the synthesis dictionary to obtain the salient low-rank and sparse coefficients. Most real data can usually be represented using a sparse and/or low-rank subspace due to the intrinsic low-dimensional characteristics [4][5][6][7][8][9][10]. Thus, without considering the joint sparse and low-rank constraints properly, the resulted structures of the coefficients may not represent the given data appropriately and accurately.…”

Section: Introductionmentioning

confidence: 99%

Learning Hybrid Representation by Robust Dictionary Learning in Factorized Compressed Space

Ren

Zhang

et al. 2020

IEEE Trans. on Image Process.

Self Cite

View full text Add to dashboard Cite

In this paper, we investigate the robust dictionary learning (DL) to discover the hybrid salient low-rank and sparse representation in a factorized compressed space. A Joint Robust Factorization and Projective Dictionary Learning (J-RFDL) model is presented. The setting of J-RFDL aims at improving the data representations by enhancing the robustness to outliers and noise in data, encoding the reconstruction error more accurately and obtaining hybrid salient coefficients with accurate reconstruction ability. Specifically, J-RFDL performs the robust representation by DL in a factorized compressed space to eliminate the negative effects of noise and outliers on the results, which can also make the DL process efficient. To make the encoding process robust to noise in data, J-RFDL clearly uses sparse L2, 1-norm that can potentially minimize the factorization and reconstruction errors jointly by forcing rows of the reconstruction errors to be zeros. To deliver salient coefficients with good structures to reconstruct given data well, J-RFDL imposes the joint low-rank and sparse constraints on the embedded coefficients with a synthesis dictionary. Based on the hybrid salient coefficients, we also extend J-RFDL for the joint classification and propose a discriminative J-RFDL model, which can improve the discriminating abilities of learnt coefficients by minimizing the classification error jointly. Extensive experiments on public datasets demonstrate that our formulations can deliver superior performance over other state-of-the-art methods. Index Terms-Hybrid salient representation, robust factorized compression, robust projective dictionary learning, classificationW ---------------- J. Ren is with the

show abstract

Discriminative Local Sparse Representation by Robust Adaptive Dictionary Pair Learning

Cited by 62 publications

References 48 publications

Identification of Underwater Targets Based on Sparse Representation

Identification of Underwater Targets Based on Sparse Representation

Genetic Algorithm Optimized Structured Dictionary for Discriminative Block Sparse Representation

Learning Hybrid Representation by Robust Dictionary Learning in Factorized Compressed Space

Contact Info

Product

Resources

About