Abstract
Discriminative dictionary learning has been extensively used for pattern classification tasks. By incorporating different kinds of label information into the dictionary learning framework, a dictionary can be attained that represents the original signal with discriminative reconstruction. The previous works learn the dictionary in the original space which limits the dictionary learning performance. In this paper, we propose an approach, namely Deep Discriminative Dictionary Pair Learning (D\(^3\)PL) for image classification. The input of D\(^3\)PL is not the matrix collected by original gray images or hand-crafted features but the relatively deeper features derived from autoencoders. Then, a structured dictionary is designed based on the discriminative contributions across different classes to reconstruct the deep feature. In addition, the associated structured projective dictionary is learned as well to guarantee the decoders updating towards the minimal error of deconvolution operator. By leveraging the discriminative-dictionary-learning-based loss function and the autoencoder loss function, D\(^3\)PL can simultaneously learn the deep potential feature and the corresponding dictionary pair. In the testing phase of D\(^3\)PL, the minimum error between the deep feature and the structured projective component with regard to different classes can directly indicate the label by a basic matrix multiplication operation. Experimental results on challenging Extended Yale B, AR, UMIST, COIL20, Scene 15, and Caltech101 datasets demonstrate that the proposed D\(^3\)PL outperforms the prominent dictionary learning methods.
Similar content being viewed by others
References
Budhiraja S, Sharma R, Agrawal S, Sohi BS (2021) Infrared and visible image fusion using modified spatial frequency-based clustered dictionary. Appl Intell 24:575–589
Hu Y, Zhang B, Jiang C, Chen Z (2022) A feature-level full-reference image denoising quality assessment method based on joint sparse representation. Appl Intell. https://doi.org/10.1007/s10489-021-03052-4
Simsek M, Polat E (2021) Performance evaluation of pan-sharpening and dictionary learning methods for sparse representation of hyperspectral super-resolution. Signal, Image Video Process 15:1099–1106
Liao M, Fan X, Li Y, Gao M (2023) Noise-related face image recognition based on double dictionary transform learning. Inform Sci 630:98–118
Dawn DD, Khan A, Shaikh SH, Pal RK (2022) A dictionary based model for bengali document classification. Appl Intell. https://doi.org/10.1007/s10489-022-03955-w
Ghasemi M, Kelarestaghi M, Eshghi F, Sharifi A (2022) D3fc: deep feature-extractor discriminative dictionary-learning fuzzy classifier for medical imaging. Appl Intell 52:7201–7217
Singh UP, Singh KP, Thakur M (2022) Meta-dzsl: a meta-dictionary learning based approach to zero-shot recognition. Appl Intell 52:15938–15960
Kang B, Zhu WP, Liang D, Chen M (2019) Robust visual tracking via nonlocal regularized multi-view sparse representation. Pattern Recogn 88:75–89
Lan X, Ma AJ, Yuen PC, Chellappa R (2015) Joint sparse representation and robust feature-level fusion for multi-cue visual tracking. IEEE Trans Image Process 24(12):5826–5841
Elhamifar E, Vidal R (2013) Sparse subspace clustering: algorithm, theory, and applications. IEEE Trans Pattern Anal Mach Intell 35(11):2765–2781
Li CG, You C, Rene V (2017) Structured sparse subspace clustering: a joint affinity learning and subspace clustering framework. IEEE Trans Image Process 26(6):2988–3001
Abdolali M, Gillis N, Rahmati M (2019) Scalable and robust sparse subspace clustering using randomized clustering and multilayer graphs. Signal Process 163:166–180
Xu G, Yang M, Wu Q (2019) Sparse subspace clustering with lowrank transformation. Neural Comput Appl 31:3141–3154
Wright J, Yang AY, Ganesh A, Sastry SS, Ma Y (2009) Robust face recognition via sparse representation. IEEE Trans Pattern Anal Mach Intell 31(2):210–227
Aharon M, Elad M, Bruckstein A (2006) K-svd: An algorithm for designing overcomplete dictionaries for sparse representation. IEEE Trans Signal Process 54(11):4311–4322
Zhang Q, Li B (2010) Discriminative k-svd for dictionary learning in face recognition
Jiang Z, Lin Z, Davis LS (2013) Label consistent k-svd: learning a discriminative dictionary for recognition. IEEE Trans Pattern Anal Mach Intell 35(11):2651–2664
Wang Z, She H, Zhang Y, Du YP (2023) Parallel non-cartesian spatialtemporal dictionary learning neural networks (stdlnn) for accelerating 4d-mri. Med Image Anal 84:102701
Sreekanth VS, Raghunath K, Mishra D (2023) Multi-resolution dictionary learning for discrimination of hidden features: A case study of atmospheric gravity waves. Signal Process 204:108831
Shan D, Li D (2022) Semi-sparse residual recurrent neural network via dictionary representation for throat microphone quality enhancement. Appl Soft Comput 129:109618
Zemouri R, Ibrahim R, Tahan A (2023) Hydrogenerator early fault detection: Sparse dictionary learning jointly with the variational autoencoder. Eng Appl Artif Intell 120:105859
Golts A, Elad M (2016) Linearized kernel dictionary learning. IEEE J Selected Topics Signal Process 10(4):726–739
Sun Y, Quan Y, Fu J (2018) Sparse coding and dictionary learning with class-specific group sparsity. Neural Comput Appl 30:1265–1275
Zhang Z et al (2018) Jointly learning structured analysis discriminative dictionary and analysis multiclass classifier. IEEE Trans Neural Netw Learn Syst 29(8):3798–3814
Chang H, Tang H, Zhang F, Chen Y, Zheng H (2019) Graphregularized discriminative analysis-synthesis dictionary pair learning for image classification. IEEE Access 7:55398–55406
Wang Y, Shao S, Xu R, Liu W, Liu B (2020) Class specific or shared? a cascaded dictionary learning framework for image classification. Signal Process 176:107697
Lu J, Wang G, Zhou J (2017) Simultaneous feature and dictionary learning for image set based face recognition. IEEE Trans Image Process 26(8):4042–4054
Mairal J, Bach F, Ponce J, Sapiro G, Zisserman A (2008) Supervised dictionary learning
Mairal J, Bach F, Ponce J (2010) Task-driven dictionary learning. IEEE Trans Pattern Anal Mach Intell 34(4):791–804
Kviatkovsky I, Gabel M, Rivlin E, Shimshoni I (2016) On the equivalence of the lc-ksvd and the d-ksvd algorithms. IEEE Trans Pattern Anal Mach Intell 39(2):411–416
Yang M, Zhang L, Feng X, Zhang D (2011) Fisher discrimination dictionary learning for sparse representation
Zhu W, Yan Y, Peng Y (2016) Dictionary learning based on discriminative energy contribution for image classification. Knowledge-Based Syst 113:116–124
Wang Z, Yang J, Nasrabadi N, Huang T (2013) A max-margin perspective on sparse representation-based classification
Gu S, Zhang L, Zuo W, Feng X (2014) Projective dictionary pair learning for pattern classification
Zhang Z, et al. (2019) Learning structured twin-incoherent twin-projective latent dictionary pairs for classification, 836-845
Zhang Z et al (2021) Twin-incoherent self-expressive locality-adaptive latent dictionary pair learning for classification. IEEE Trans Neural Netw Learn Syst 323:947–961
Tariyal S, Majumdar A, Singh R, Vatsa M (2016) Deep dictionary learning. IEEE Access 4:10096–10109
Singhal V, Aggarwal HK, Tariyal S, Majumdar A (2017) Discriminative robust deep dictionary learning for hyperspectral image classification. IEEE Trans Geoscience Remote Sens 55(9):5274–5283
Pang, X, Yang C, Zhang Z, You X, Zhang C (2019) A channel-blind decoding for ldpc based on deep learning and dictionary learning, 284-289
Zhang, L, Yang M, Feng X (2011) Sparse representation or collaborative representation: which helps face recognition?
Krizhevsky A, Sutskever I, Hinton G (2012) Imagenet classification with deep convolutional neural networks
Elhamifar E, Vidal R (2011) Robust classification using structured sparse representation
Michael G, Stephen B (2013) Cvx: Matlab software for disciplined convex programming, version 2.0 beta
Cai S, Zuo W, Zhang L, Feng X, Wang P (2014) Support vector guided dictionary learning
Wang Y, Du H, Zhang Y, Zhang Y (2021) Efficient and robust discriminant dictionary pair learning for pattern classification. Digital Signal Process 118:103227
Dong J, Yang L, Liu C, Cheng W, Wang W (2022) Support vector machine embedding discriminative dictionary pair learning for pattern classification. Neural Netw 155:498–511
Ji P, Zhang T, Li H, Salzmann M, Reid I (2017) Deep subspace clustering networks
Zhang J, et al. (2019) Self-supervised convolutional subspace clustering network, 5468-5477
Acknowledgements
This research was partially supported by the National Key Research and Development Program of China under Grant No. 2021YFC3340402, the Key Research and Development Project of Zhejiang Province under Grant No. 2021C03151, Zhejiang Provincial Natural Science Foundation of China under Grant No. LQ20F030015, the Fundamental Research Funds for the Provincial Universities of Zhejiang under Grant No. 2022YW40, and China Jiliang University Student Research Program No. 2022X25037.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Wenjie Zhu and Bo Peng contributed equally to this work.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Zhu, W., Peng, B., Chen, C. et al. Deep discriminative dictionary pair learning for image classification. Appl Intell 53, 22017–22030 (2023). https://doi.org/10.1007/s10489-023-04708-z
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-023-04708-z