Jointly Learning Structured Analysis Discriminative Dictionary and Analysis Multiclass Classifier

Zhang, Zhao; Jiang, Weizhong; Qin, Jie; Zhang, Li; Li, Fanzhang; Zhang, Min; Yan, Shuicheng

doi:10.1109/tnnls.2017.2740224

Cited by 145 publications

(91 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For larger datasets such as MNIST and Fashion-MNIST, the loss is non-increasing in iterations and finally converges. [5] 90.30% 91.58% DKSVD [7] 92.31% 92.92% LC-KSVD1 [1] 93.67% 95.01% LC-KSVD2 [1] 94.49% 95.91% DLSI [9] 95.48% 96.13% FDDL [8] 95.38% 96.00% DPL [10] 94.20% 95.00% LRSDL [19] 96.26% 96.85% ADDL [12] 95.90% 96.30% SCN-2 [6] 96.37% 97.53% CDPL-Net (no DPL layers) 96.20% 97.44% Our CDPL-Net 97.70% 98.48%…”

Section: Convergence Analysismentioning

confidence: 99%

“…DL obtains the sparse representation of samples via a linear combination of atoms in a dictionary. Classical DL algorithms include K-Singular Value Decomposition (K-SVD) [4], Discriminative K-SVD (D-KSVD) [7], Label-Consistent K-SVD (LC-KSVD) [1], Fisher Discrimination Dictionary Learning (FDDL) [8], Dictionary Learning with Structured Incoherence (DLSI) [9], Structured Analysis Discriminative Dictionary Learning (ADDL) [12], Projective Dictionary Pair Learning (DPL) [10] and Low-rank Shared Dictionary Learning (LRSDL) [19], etc. Compared with the other existing methods, both DPL and ADDL extend the regular DL into the dictionary pair learning, i.e., learning a synthesis dictionary and an analysis dictionary jointly to analytically code data.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Convolutional Dictionary Pair Learning Network for Image Representation Learning.pdf

Zhang¹,

Sun²,

Wang³

et al. 2019

Preprint

Self Cite

View full text Add to dashboard Cite

Both the Dictionary Learning (DL) and Convolutional Neural Networks (CNN) are powerful image representation learning systems based on different mechanisms and principles, however whether we can seamlessly integrate them to improve the performance is noteworthy exploring. To address this issue, we propose a novel generalized end-to-end representation learning architecture, dubbed Convolutional Dictionary Pair Learning Network (CDPL-Net) in this paper, which integrates the learning schemes of the CNN and dictionary pair learning into a unified framework. Generally, the architecture of CDPL-Net includes two convolutional/pooling layers and two dictionary pair learning (DPL) layers in the representation learning module. Besides, it uses two fullyconnected layers as the multi-layer perception layer in the nonlinear classification module. In particular, the DPL layer can jointly formulate the discriminative synthesis and analysis representations driven by minimizing the batch based reconstruction error over the flatted feature maps from the convolution/pooling layer. Moreover, DPL layer uses l1-norm on the analysis dictionary so that sparse representation can be delivered, and the embedding process will also be robust to noise. To speed up the training process of DPL layer, the efficient stochastic gradient descent is used. Extensive simulations on real databases show that our CDPL-Net can deliver enhanced performance over other state-of-the-art methods. 1

show abstract

Section: Convergence Analysismentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Convolutional Dictionary Pair Learning Network for Image Representation Learning.pdf

Zhang¹,

Sun²,

Wang³

et al. 2019

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, CS theory states that if x j is sufficiently sparse in a transform (Ψ Ψ Ψ) domain, exact recovery is possible. Several recovery methods have been developed for this purpose [34], [35], [36], [37]. Specifically, if the transform coefficients, v j = Ψ Ψ Ψx j , are sufficiently sparse, the solution of the recovery procedure can be found with several l 0 optimization procedures or their l 1 -based convex relaxations that use pursuit-based methods [15], [16].…”

Section: Introductionmentioning

confidence: 99%

Soft Video Multicasting Using Adaptive Compressed Sensing

Hadizadeh

Bajić

2021

IEEE Trans. Multimedia

View full text Add to dashboard Cite

Recently, soft video multicasting has gained a lot of attention, especially in broadcast and mobile scenarios where the bit rate supported by the channel may differ across receivers, and may vary quickly over time. Unlike the conventional designs that force the source to use a single bit rate according to the receiver with the worst channel quality, soft video delivery schemes transmit the video such that the video quality at each receiver is commensurate with its specific instantaneous channel quality. In this paper, we present a soft video multicasting system using an adaptive block-based compressed sensing (BCS) method. The proposed system consists of an encoder, a transmission system, and a decoder. At the encoder side, each block in each frame of the input video is adaptively sampled with a rate that depends on the texture complexity and visual saliency of the block. The obtained BCS samples are then placed into several packets, and the packets are transmitted via a channel-aware OFDM (orthogonal frequency division multiplexing) transmission system with a number of subchannels. At the decoder side, the received BCS samples are first used to build an initial approximation of the transmitted frame. To further improve the reconstruction quality, an iterative BCS reconstruction algorithm is then proposed that uses an adaptive transform and an adaptive soft-thresholding operator, which exploits the temporal similarity between adjacent frames to achieve better reconstruction quality. The extensive objective and subjective experimental results indicate the superiority of the proposed system over the state-of-the-art soft video multicasting systems.

show abstract

“…The second .. category aims at learning the category-specific dictionaries to improve the discrimination by assigning each sub-dictionary to a single subject class, i.e., structured dictionary learning. In this category, popular methods are Low-rank Shared DL (LRSDL) [52], Analysis Discriminative Dictionary Learning (ADDL) [22], Dictionary Learning with Structured Incoherence (DLSI) [21] and Projective Dictionary Pair Learning (DPL) [17]. DPL aims to obtain a structured synthesis dictionary and an analysis dictionary jointly, and ADDL is based on the idea of DPL and it aims to compute a structured analysis discriminative dictionary and an analysis multiclass classifier.…”

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

Jointly Learning Structured Analysis Discriminative Dictionary and Analysis Multiclass Classifier

Cited by 145 publications

References 40 publications

Convolutional Dictionary Pair Learning Network for Image Representation Learning.pdf

Convolutional Dictionary Pair Learning Network for Image Representation Learning.pdf

Soft Video Multicasting Using Adaptive Compressed Sensing

Learning Hybrid Representation by Robust Dictionary Learning in Factorized Compressed Space

Contact Info

Product

Resources

About