WARP-LCA: Efficient convolutional sparse coding with Locally Competitive Algorithm
The locally competitive algorithm (LCA) can solve sparse coding problems across a wide range of use cases. Recently, convolution-based LCA approaches have been shown to be highly effective for enhancing robustness for image recognition tasks in vision pipelines. To additionally maximize representati...
Uloženo v:
| Vydáno v: | Neurocomputing (Amsterdam) Ročník 640; s. 130291 |
|---|---|
| Hlavní autoři: | , , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Elsevier B.V
01.08.2025
|
| Témata: | |
| ISSN: | 0925-2312 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | The locally competitive algorithm (LCA) can solve sparse coding problems across a wide range of use cases. Recently, convolution-based LCA approaches have been shown to be highly effective for enhancing robustness for image recognition tasks in vision pipelines. To additionally maximize representational sparsity, LCA with hard-thresholding can be applied. While this combination often yields very good solutions satisfying an ℓ0 sparsity criterion, it comes with significant drawbacks for practical application: (i) LCA is very inefficient, typically requiring hundreds of optimization cycles for convergence; (ii) the use of a hard-thresholding results in a non-convex loss function, which might lead to suboptimal minima. To address these issues, we propose the Locally Competitive Algorithm with State Warm-up via Predictive Priming (WARP-LCA), which leverages a predictor network to provide a suitable initial guess of the LCA state based on the current input. Our approach significantly improves both convergence speed and the quality of solutions, while maintaining and even enhancing the overall strengths of LCA. We demonstrate that WARP-LCA converges faster by orders of magnitude and reaches better minima compared to conventional LCA. Moreover, the learned representations are more sparse and exhibit superior properties in terms of reconstruction and denoising quality as well as robustness when applied in deep recognition pipelines. Furthermore, we apply WARP-LCA to image denoising tasks, showcasing its robustness and practical effectiveness. Our findings confirm that the naive use of LCA with hard-thresholding results in suboptimal minima, whereas initializing LCA with a predictive guess results in much better outcomes.
[Display omitted]
•WARP-LCA accelerates convergence and achieves superior sparsity compared to LCA.•Achieves higher PSNR and SSIM with fewer iterations than traditional LCA.•Improves denoising in classification pipelines under varying noise levels.•Enables generalizable and efficient sparse coding with predictive initialization. |
|---|---|
| AbstractList | The locally competitive algorithm (LCA) can solve sparse coding problems across a wide range of use cases. Recently, convolution-based LCA approaches have been shown to be highly effective for enhancing robustness for image recognition tasks in vision pipelines. To additionally maximize representational sparsity, LCA with hard-thresholding can be applied. While this combination often yields very good solutions satisfying an ℓ0 sparsity criterion, it comes with significant drawbacks for practical application: (i) LCA is very inefficient, typically requiring hundreds of optimization cycles for convergence; (ii) the use of a hard-thresholding results in a non-convex loss function, which might lead to suboptimal minima. To address these issues, we propose the Locally Competitive Algorithm with State Warm-up via Predictive Priming (WARP-LCA), which leverages a predictor network to provide a suitable initial guess of the LCA state based on the current input. Our approach significantly improves both convergence speed and the quality of solutions, while maintaining and even enhancing the overall strengths of LCA. We demonstrate that WARP-LCA converges faster by orders of magnitude and reaches better minima compared to conventional LCA. Moreover, the learned representations are more sparse and exhibit superior properties in terms of reconstruction and denoising quality as well as robustness when applied in deep recognition pipelines. Furthermore, we apply WARP-LCA to image denoising tasks, showcasing its robustness and practical effectiveness. Our findings confirm that the naive use of LCA with hard-thresholding results in suboptimal minima, whereas initializing LCA with a predictive guess results in much better outcomes.
[Display omitted]
•WARP-LCA accelerates convergence and achieves superior sparsity compared to LCA.•Achieves higher PSNR and SSIM with fewer iterations than traditional LCA.•Improves denoising in classification pipelines under varying noise levels.•Enables generalizable and efficient sparse coding with predictive initialization. |
| ArticleNumber | 130291 |
| Author | Ecke, Gerrit Otte, Sebastian Kasenbacher, Geoffrey Ehret, Felix |
| Author_xml | – sequence: 1 givenname: Geoffrey surname: Kasenbacher fullname: Kasenbacher, Geoffrey email: geoffrey.kasenbacher@mercedes-benz.com organization: Mercedes-Benz AG, Leibnizstraße 2, Böblingen, Germany – sequence: 2 givenname: Felix surname: Ehret fullname: Ehret, Felix organization: Mercedes-Benz AG, Leibnizstraße 2, Böblingen, Germany – sequence: 3 givenname: Gerrit surname: Ecke fullname: Ecke, Gerrit organization: Mercedes-Benz AG, Leibnizstraße 2, Böblingen, Germany – sequence: 4 givenname: Sebastian surname: Otte fullname: Otte, Sebastian organization: Institut für Robotik und Kognitive Systeme, Universität zu Lübeck, Ratzeburger Allee 160, Lübeck, Germany |
| BookMark | eNp9kMtqwzAURLVIoUnaP-hCP2D3Soof6qJgTPoAQ0to6VLIkpwq2FaQHJf8fR3cdVcX5jLDzFmhRe96g9AdgZgASe8PcW9OynUxBZrEhAHlZIGWwGkSUUboNVqFcAAgGaF8iXZfxe49qsriAW-bxipr-gEr14-uPQ3W9bLF4Sh9MJOobb_HP3b4xpVTsm3PuHTd0Qx2sKPBRbt3fnp2N-iqkW0wt393jT6fth_lS1S9Pb-WRRUpmmRDlKuszlVNEsibtOYsAdpQYBvOIYVaQ0qUlJBrprRMFcsl5RQkMU1qFMt0zdZoM-cq70LwphFHbzvpz4KAuLAQBzGzEBcWYmYx2R5nm5m6jdZ4ES6rldHWGzUI7ez_Ab81fW4J |
| Cites_doi | 10.1145/3589737.3605973 10.1162/neco.2008.03-07-486 10.1080/net.12.3.241.253 10.1109/TMI.2021.3054167 10.1038/381607a0 10.1109/TSP.2020.2976585 10.1109/TNNLS.2012.2197412 10.1371/journal.pcbi.1008629 10.1145/3546790.3546811 10.1371/journal.pcbi.1006766 10.1109/TSP.2015.2420535 10.1111/j.2517-6161.1996.tb02080.x 10.1109/MSP.2020.3016905 10.1016/j.neunet.2020.12.016 10.1109/CVPR.2018.00196 10.1007/s10915-023-02250-1 10.1145/1553374.1553463 10.1162/neco.1994.6.4.559 10.1016/j.engappai.2018.09.014 10.1137/151003714 10.1371/journal.pcbi.1006908 10.1016/S0893-6080(00)00026-5 10.1109/ICCV.2017.627 10.1016/j.artmed.2017.05.006 10.1109/CVPR.2017.243 10.1109/JPROC.2021.3067593 10.1109/ACCESS.2015.2430359 10.1137/080716542 10.1109/TIP.2020.3044472 |
| ContentType | Journal Article |
| Copyright | 2025 The Authors |
| Copyright_xml | – notice: 2025 The Authors |
| DBID | 6I. AAFTH AAYXX CITATION |
| DOI | 10.1016/j.neucom.2025.130291 |
| DatabaseName | ScienceDirect Open Access Titles Elsevier:ScienceDirect:Open Access CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| ExternalDocumentID | 10_1016_j_neucom_2025_130291 S0925231225009634 |
| GroupedDBID | --- --K --M .DC .~1 0R~ 123 1B1 1~. 1~5 4.4 457 4G. 53G 5VS 6I. 7-5 71M 8P~ 9JM 9JN AABNK AAEDT AAEDW AAFTH AAIKJ AAKOC AALRI AAOAW AAQFI AATTM AAXKI AAXLA AAXUO AAYFN AAYWO ABBOA ABCQJ ABFNM ABJNI ABMAC ACDAQ ACGFS ACRLP ACVFH ACZNC ADBBV ADCNI ADEZE AEBSH AEIPS AEKER AENEX AEUPX AFJKZ AFPUW AFTJW AFXIZ AGCQF AGHFR AGRNS AGUBO AGWIK AGYEJ AHHHB AHZHX AIALX AIEXJ AIGII AIIUN AIKHN AITUG AKBMS AKRWK AKYEP ALMA_UNASSIGNED_HOLDINGS AMRAJ ANKPU AOUOD APXCP AXJTR BKOJK BLXMC BNPGV CS3 DU5 EBS EFJIC EO8 EO9 EP2 EP3 F5P FDB FIRID FNPLU FYGXN G-Q GBLVA GBOLZ IHE J1W KOM LG9 M41 MO0 MOBAO N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 ROL RPZ SDF SDG SDP SES SEW SPC SPCBC SSH SSN SSV SSZ T5K ZMT ~G- 29N 9DU AAQXK AAYXX ABWVN ABXDB ACLOT ACNNM ACRPL ADJOM ADMUD ADNMO AGQPQ ASPBG AVWKF AZFZN CITATION EFKBS EFLBG EJD FEDTE FGOYB HLZ HVGLF HZ~ R2- SBC WUQ XPP ~HD |
| ID | FETCH-LOGICAL-c257t-8c7b8cb1508f6b93502f203499060bd061caa08d3cda6c38a2920a1ef6ec37db3 |
| ISICitedReferencesCount | 0 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001487662200001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0925-2312 |
| IngestDate | Sat Nov 29 07:51:23 EST 2025 Sat Jun 21 16:53:04 EDT 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Computer vision Convolutional sparse coding Locally competitive algorithms |
| Language | English |
| License | This is an open access article under the CC BY-NC-ND license. |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c257t-8c7b8cb1508f6b93502f203499060bd061caa08d3cda6c38a2920a1ef6ec37db3 |
| OpenAccessLink | https://dx.doi.org/10.1016/j.neucom.2025.130291 |
| ParticipantIDs | crossref_primary_10_1016_j_neucom_2025_130291 elsevier_sciencedirect_doi_10_1016_j_neucom_2025_130291 |
| PublicationCentury | 2000 |
| PublicationDate | 2025-08-01 2025-08-00 |
| PublicationDateYYYYMMDD | 2025-08-01 |
| PublicationDate_xml | – month: 08 year: 2025 text: 2025-08-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationTitle | Neurocomputing (Amsterdam) |
| PublicationYear | 2025 |
| Publisher | Elsevier B.V |
| Publisher_xml | – name: Elsevier B.V |
| References | Barlow (b3) 2001; 12 Beck, Teboulle (b25) 2009; 2 Dibbo, Breuer, Moore, Teti (b60) 2025 Boutin, Franciosini, Chavane, Ruffier, Perrinet (b59) 2021; 17 Diamond, Sitzmann, Heide, Wetzstein (b45) 2017 J. Mairal, F. Bach, J. Ponce, G. Sapiro, Online dictionary learning for sparse coding, in: Proceedings of the 26th Annual International Conference on Machine Learning, 2009, pp. 689–696. Xu, Chang, Xu, Zhang (b56) 2012; 23 Soubies, Blanc-Féraud, Aubert (b58) 2015; 8 K. Gregor, Y. LeCun, Learning fast approximations of sparse coding, in: Proceedings of the 27th International Conference on Machine Learning, ICML- 10, 2010, pp. 399–406. Dibbo, Moore, Kenyon, Teti (b16) 2023 Davies, Wild, Orchard, Sandamirskaya, Guerra, Joshi, Plank, Risbud (b20) 2021; 109 Barlow (b9) 1987 Krizhevsky, Hinton (b47) 2009 Nickson (b51) 2019 Lundquist, Mitchell, Kenyon (b12) 2017 Hyvärinen, Oja (b37) 2000; 13 Olshausen, Field (b4) 1996; 381 Zhang, Liu, Liu, Wen, Zhu (b28) 2020; 30 He, Wen, Jin, Li (b43) 2020; 68 Rigamonti, Brown, Lepetit (b10) 2011 Lundquist, Paiton, Schultz, Kenyon (b11) 2016 Lee, Ekanadham, Ng (b6) 2007; 20 Monga, Li, Eldar (b44) 2021; 38 Dibbo, Moore, Kenyon, Teti (b62) 2024 Lee, Battle, Raina, Ng (b5) 2006 Lecouat, Ponce, Mairal (b17) 2020 Coates, Lee, Ng (b48) 2011 Beyeler, Rounds, Carlson, Dutt, Krichmar (b7) 2019; 15 Lang, Giese, Ilg, Otte (b46) 2023 Field (b2) 1994; 6 Li, Osher (b23) 2009; 50 Nguyen, Soussen, Idier, Djermoune (b33) 2019 Takaghaj, Sampson (b61) 2024 Vonesch, Unser (b26) 2007; 55 Zhang, Xu, Yang, Li, Zhang (b31) 2015; 3 Parkhi, Vedaldi, Zisserman, Jawahar (b50) 2012 Rozell, Johnson, Baraniuk, Olshausen (b35) 2007; Vol. 4 Zhang, Shen, Wei, Li, Sangaiah (b13) 2017; 83 Xin, Wang, Gao, Wipf, Wang (b41) 2016 Teti, Kenyon, Migliori, Moore (b18) 2022 G. Parpart, S. Risbud, G. Kenyon, Y. Watkins, Implementing and Benchmarking the Locally Competitive Algorithm on the Loihi 2 Neuromorphic Processor, in: Proceedings of the 2023 International Conference on Neuromorphic Systems, 2023, pp. 1–6. Sambharya, Hall, Amos, Stellato (b38) 2023 Zhang, Hu, Hong, Zhang (b15) 2019; 15 Klaučo, Kalúz, Kvasnica (b39) 2019; 77 Rozell, Johnson, Baraniuk, Olshausen (b19) 2008; 20 Paiton (b32) 2019 J. Rick Chang, C.-L. Li, B. Poczos, B. Vijaya Kumar, A.C. Sankaranarayanan, One network to solve them all–solving linear inverse problems using deep projection models, in: Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 5888–5897. Sjölund, Bånkestad (b40) 2022 Liang, Wang, Yu (b57) 2023; 96 Barlow (b1) 1961; 1 Ecke, Papp, Mallot (b8) 2021; 135 Li, Karpathy, Johnson (b49) 2017 Xiang, Dong, Yang (b29) 2021; 40 J. Zhang, B. Ghanem, ISTA-Net: Interpretable optimization-inspired deep network for image compressive sensing, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 1828–1837. Xie, Girshick, Dollár, Tu, He (b54) 2017 Balavoine, Rozell, Romberg (b34) 2015; 63 K. Henke, M. Teti, G. Kenyon, B. Migliori, G. Kunde, Apples-to-spikes: The first detailed comparison of LASSO solutions generated by a spiking neuromorphic processor, in: Proceedings of the International Conference on Neuromorphic Systems 2022, 2022, pp. 1–8. Calatroni, Perrinet, Prandi (b55) 2023; 19 Kim, Hannan, Kenyon (b14) 2018 Zagoruyko, Komodakis (b53) 2016 G. Huang, Z. Liu, L. Van Der Maaten, K.Q. Weinberger, Densely connected convolutional networks, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 4700–4708. Tibshirani (b36) 1996; 58 Sjölund (10.1016/j.neucom.2025.130291_b40) 2022 Zhang (10.1016/j.neucom.2025.130291_b31) 2015; 3 Xie (10.1016/j.neucom.2025.130291_b54) 2017 10.1016/j.neucom.2025.130291_b27 Davies (10.1016/j.neucom.2025.130291_b20) 2021; 109 Lecouat (10.1016/j.neucom.2025.130291_b17) 2020 10.1016/j.neucom.2025.130291_b21 10.1016/j.neucom.2025.130291_b22 Calatroni (10.1016/j.neucom.2025.130291_b55) 2023; 19 10.1016/j.neucom.2025.130291_b24 He (10.1016/j.neucom.2025.130291_b43) 2020; 68 Beyeler (10.1016/j.neucom.2025.130291_b7) 2019; 15 10.1016/j.neucom.2025.130291_b30 Dibbo (10.1016/j.neucom.2025.130291_b60) 2025 Ecke (10.1016/j.neucom.2025.130291_b8) 2021; 135 Beck (10.1016/j.neucom.2025.130291_b25) 2009; 2 Balavoine (10.1016/j.neucom.2025.130291_b34) 2015; 63 Monga (10.1016/j.neucom.2025.130291_b44) 2021; 38 Kim (10.1016/j.neucom.2025.130291_b14) 2018 Nickson (10.1016/j.neucom.2025.130291_b51) 2019 Barlow (10.1016/j.neucom.2025.130291_b1) 1961; 1 Xiang (10.1016/j.neucom.2025.130291_b29) 2021; 40 Soubies (10.1016/j.neucom.2025.130291_b58) 2015; 8 Field (10.1016/j.neucom.2025.130291_b2) 1994; 6 Krizhevsky (10.1016/j.neucom.2025.130291_b47) 2009 Parkhi (10.1016/j.neucom.2025.130291_b50) 2012 Zhang (10.1016/j.neucom.2025.130291_b28) 2020; 30 Dibbo (10.1016/j.neucom.2025.130291_b16) 2023 10.1016/j.neucom.2025.130291_b42 Barlow (10.1016/j.neucom.2025.130291_b3) 2001; 12 Paiton (10.1016/j.neucom.2025.130291_b32) 2019 Zagoruyko (10.1016/j.neucom.2025.130291_b53) 2016 Zhang (10.1016/j.neucom.2025.130291_b13) 2017; 83 Zhang (10.1016/j.neucom.2025.130291_b15) 2019; 15 Lundquist (10.1016/j.neucom.2025.130291_b11) 2016 Vonesch (10.1016/j.neucom.2025.130291_b26) 2007; 55 Sambharya (10.1016/j.neucom.2025.130291_b38) 2023 Xu (10.1016/j.neucom.2025.130291_b56) 2012; 23 Olshausen (10.1016/j.neucom.2025.130291_b4) 1996; 381 Rozell (10.1016/j.neucom.2025.130291_b35) 2007; Vol. 4 Tibshirani (10.1016/j.neucom.2025.130291_b36) 1996; 58 Klaučo (10.1016/j.neucom.2025.130291_b39) 2019; 77 Lang (10.1016/j.neucom.2025.130291_b46) 2023 Diamond (10.1016/j.neucom.2025.130291_b45) 2017 Coates (10.1016/j.neucom.2025.130291_b48) 2011 10.1016/j.neucom.2025.130291_b52 Lee (10.1016/j.neucom.2025.130291_b6) 2007; 20 Nguyen (10.1016/j.neucom.2025.130291_b33) 2019 Xin (10.1016/j.neucom.2025.130291_b41) 2016 Rigamonti (10.1016/j.neucom.2025.130291_b10) 2011 Liang (10.1016/j.neucom.2025.130291_b57) 2023; 96 Li (10.1016/j.neucom.2025.130291_b49) 2017 Boutin (10.1016/j.neucom.2025.130291_b59) 2021; 17 Li (10.1016/j.neucom.2025.130291_b23) 2009; 50 Takaghaj (10.1016/j.neucom.2025.130291_b61) 2024 Lee (10.1016/j.neucom.2025.130291_b5) 2006 Rozell (10.1016/j.neucom.2025.130291_b19) 2008; 20 Lundquist (10.1016/j.neucom.2025.130291_b12) 2017 Dibbo (10.1016/j.neucom.2025.130291_b62) 2024 Hyvärinen (10.1016/j.neucom.2025.130291_b37) 2000; 13 Barlow (10.1016/j.neucom.2025.130291_b9) 1987 Teti (10.1016/j.neucom.2025.130291_b18) 2022 |
| References_xml | – start-page: 215 year: 2011 end-page: 223 ident: b48 article-title: An analysis of single-layer networks in unsupervised feature learning publication-title: Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics – year: 2022 ident: b40 article-title: Graph-based neural acceleration for nonnegative matrix factorization – volume: 20 start-page: 2526 year: 2008 end-page: 2563 ident: b19 article-title: Sparse coding via thresholding and local competition in neural circuits publication-title: Neural Comput. – start-page: 238 year: 2020 end-page: 254 ident: b17 article-title: Fully trainable and interpretable non-local sparse models for image restoration publication-title: Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XXII 16 – volume: 77 start-page: 1 year: 2019 end-page: 8 ident: b39 article-title: Machine learning-based warm starting of active set methods in embedded model predictive control publication-title: Eng. Appl. Artif. Intell. – volume: 8 start-page: 1607 year: 2015 end-page: 1639 ident: b58 article-title: A continuous exact publication-title: SIAM J. Imaging Sci. – volume: 38 start-page: 18 year: 2021 end-page: 44 ident: b44 article-title: Algorithm unrolling: Interpretable, efficient deep learning for signal and image processing publication-title: IEEE Signal Process. Mag. – volume: 63 start-page: 3165 year: 2015 end-page: 3176 ident: b34 article-title: Discrete and continuous-time soft-thresholding for dynamic signal recovery publication-title: IEEE Trans. Signal Process. – start-page: 395 year: 1987 end-page: 406 ident: b9 article-title: Cerebral cortex as model builder publication-title: Matters of Intelligence: Conceptual Structures in Cognitive Neuroscience – volume: 109 start-page: 911 year: 2021 end-page: 934 ident: b20 article-title: Advancing neuromorphic computing with loihi: A survey of results and outlook publication-title: Proc. IEEE – start-page: 4340 year: 2016 end-page: 4348 ident: b41 article-title: Maximal sparsity with deep networks? publication-title: Advances in Neural Information Processing Systems – year: 2017 ident: b12 article-title: Sparse coding on stereo video for object detection – volume: 13 start-page: 411 year: 2000 end-page: 430 ident: b37 article-title: Independent component analysis: algorithms and applications publication-title: Neural Netw. – volume: 15 year: 2019 ident: b15 article-title: A hierarchical sparse coding model predicts acoustic feature encoding in both auditory midbrain and cortex publication-title: PLoS Comput. Biol. – start-page: 1 year: 2019 end-page: 4 ident: b33 article-title: NP-hardness of publication-title: 2019 13th International Conference on Sampling Theory and Applications – start-page: 117 year: 2025 end-page: 136 ident: b60 article-title: Improving robustness to model inversion attacks via sparse coding architectures publication-title: European Conference on Computer Vision – year: 2017 ident: b49 article-title: Tiny ImageNet visual recognition challenge – year: 2018 ident: b14 article-title: Deep sparse coding for invariant multimodal halle berry neurons publication-title: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition – volume: 68 start-page: 1702 year: 2020 end-page: 1715 ident: b43 article-title: Model-driven deep learning for MIMO detection publication-title: IEEE Trans. Signal Process. – volume: 19 year: 2023 ident: b55 article-title: Beyond l1 sparse coding in V1 publication-title: PLoS Comput. Biol. – year: 2023 ident: b16 article-title: LCANets++: Robust audio classification using multi-layer neural networks with lateral competition – volume: 6 start-page: 559 year: 1994 end-page: 601 ident: b2 article-title: What is the goal of sensory coding? publication-title: Neural Comput. – start-page: 1492 year: 2017 end-page: 1500 ident: b54 article-title: Aggregated residual transformations for deep neural networks publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – volume: 58 start-page: 267 year: 1996 end-page: 288 ident: b36 article-title: Regression Shrinkage and Selection Via the Lasso publication-title: J. R. Stat. Soc. Ser. B Stat. Methodol. – year: 2017 ident: b45 article-title: Unrolled optimization with deep priors – volume: 15 year: 2019 ident: b7 article-title: Neural correlates of sparse coding and dimensionality reduction publication-title: PLoS Comput. Biol. – year: 2019 ident: b51 article-title: Breathtaking kalalau valley scenic view – volume: 12 start-page: 241 year: 2001 end-page: 253 ident: b3 article-title: Redundancy reduction revisited publication-title: Netw., Comput. Neural Syst. – volume: 17 year: 2021 ident: b59 article-title: Sparse deep predictive coding captures contour integration capabilities of the early visual system publication-title: PLoS Comput. Biol. – reference: G. Huang, Z. Liu, L. Van Der Maaten, K.Q. Weinberger, Densely connected convolutional networks, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 4700–4708. – year: 2023 ident: b38 article-title: Learning to warm-start fixed-point optimization algorithms – start-page: 21232 year: 2022 end-page: 21252 ident: b18 article-title: LCANets: Lateral competition improves robustness against corruption and attack publication-title: International Conference on Machine Learning – reference: K. Henke, M. Teti, G. Kenyon, B. Migliori, G. Kunde, Apples-to-spikes: The first detailed comparison of LASSO solutions generated by a spiking neuromorphic processor, in: Proceedings of the International Conference on Neuromorphic Systems 2022, 2022, pp. 1–8. – volume: 30 start-page: 1487 year: 2020 end-page: 1500 ident: b28 article-title: AMP-Net: Denoising-based deep unfolding for compressive image sensing publication-title: IEEE Trans. Image Process. – volume: 381 start-page: 607 year: 1996 end-page: 609 ident: b4 article-title: Emergence of simple-cell receptive field properties by learning a sparse code for natural images publication-title: Nature – year: 2016 ident: b53 article-title: Wide residual networks – year: 2019 ident: b32 article-title: Analysis and applications of the Locally Competitive Algorithm – reference: J. Rick Chang, C.-L. Li, B. Poczos, B. Vijaya Kumar, A.C. Sankaranarayanan, One network to solve them all–solving linear inverse problems using deep projection models, in: Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 5888–5897. – volume: 96 start-page: 61 year: 2023 ident: b57 article-title: A reduced half thresholding algorithm publication-title: J. Sci. Comput. – start-page: 129 year: 2024 end-page: 133 ident: b62 article-title: LCANets++: Robust audio classification using multi-layer neural networks with lateral competition publication-title: 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops – year: 2011 ident: b10 article-title: Are sparse representations really relevant for image classification? publication-title: CVPR 2011 – volume: 23 start-page: 1013 year: 2012 end-page: 1027 ident: b56 article-title: L publication-title: IEEE Trans. Neural Netw. Learn. Syst. – volume: 135 start-page: 158 year: 2021 end-page: 176 ident: b8 article-title: Exploitation of image statistics with sparse coding in the case of stereo vision publication-title: Neural Netw. – start-page: 180 year: 2023 end-page: 193 ident: b46 article-title: Generating sparse counterfactual explanations for multivariate time series publication-title: International Conference on Artificial Neural Networks – reference: J. Mairal, F. Bach, J. Ponce, G. Sapiro, Online dictionary learning for sparse coding, in: Proceedings of the 26th Annual International Conference on Machine Learning, 2009, pp. 689–696. – start-page: 3498 year: 2012 end-page: 3505 ident: b50 article-title: Cats and dogs publication-title: 2012 IEEE Conference on Computer Vision and Pattern Recognition – volume: 3 start-page: 490 year: 2015 end-page: 530 ident: b31 article-title: A survey of sparse representation: algorithms and applications publication-title: IEEE Access – volume: 50 start-page: 65 year: 2009 end-page: 79 ident: b23 article-title: Compressed sensing and matrix completion with uniform uncertainty principle publication-title: SIAM Rev. – year: 2016 ident: b11 article-title: Sparse encoding of binocular images for depth inference publication-title: 2016 IEEE Southwest Symposium on Image Analysis and Interpretation – start-page: 801 year: 2006 end-page: 808 ident: b5 article-title: Efficient sparse coding algorithms publication-title: Advances in Neural Information Processing Systems – reference: K. Gregor, Y. LeCun, Learning fast approximations of sparse coding, in: Proceedings of the 27th International Conference on Machine Learning, ICML- 10, 2010, pp. 399–406. – year: 2009 ident: b47 article-title: Learning multiple layers of features from tiny images – reference: J. Zhang, B. Ghanem, ISTA-Net: Interpretable optimization-inspired deep network for image compressive sensing, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 1828–1837. – volume: 2 start-page: 183 year: 2009 end-page: 202 ident: b25 article-title: A fast iterative shrinkage-thresholding algorithm for linear inverse problems publication-title: SIAM J. Imaging Sci. – volume: Vol. 4 start-page: IV year: 2007 end-page: 169 ident: b35 article-title: Locally competitive algorithms for sparse approximation publication-title: 2007 IEEE International Conference on Image Processing – volume: 55 start-page: 482 year: 2007 end-page: 492 ident: b26 article-title: A generalized forward-backward splitting algorithm for sparse signal recovery publication-title: IEEE Trans. Signal Process. – reference: G. Parpart, S. Risbud, G. Kenyon, Y. Watkins, Implementing and Benchmarking the Locally Competitive Algorithm on the Loihi 2 Neuromorphic Processor, in: Proceedings of the 2023 International Conference on Neuromorphic Systems, 2023, pp. 1–6. – volume: 40 start-page: 1329 year: 2021 end-page: 1339 ident: b29 article-title: FISTA-net: Learning a fast iterative shrinkage thresholding network for inverse problems in imaging publication-title: IEEE Trans. Med. Imaging – year: 2024 ident: b61 article-title: Exemplar LCA-decoder: A scalable framework for on-chip learning – volume: 1 start-page: 217 year: 1961 end-page: 233 ident: b1 article-title: Possible principles underlying the transformation of sensory messages publication-title: Sens. Commun. – volume: 20 year: 2007 ident: b6 article-title: Sparse deep belief net model for visual area V2 publication-title: Adv. Neural Inf. Process. Syst. – volume: 83 start-page: 44 year: 2017 end-page: 51 ident: b13 article-title: Medical image classification based on multi-scale non-negative sparse coding publication-title: Artif. Intell. Med. – ident: 10.1016/j.neucom.2025.130291_b22 doi: 10.1145/3589737.3605973 – year: 2017 ident: 10.1016/j.neucom.2025.130291_b49 – start-page: 801 year: 2006 ident: 10.1016/j.neucom.2025.130291_b5 article-title: Efficient sparse coding algorithms – start-page: 395 year: 1987 ident: 10.1016/j.neucom.2025.130291_b9 article-title: Cerebral cortex as model builder – year: 2023 ident: 10.1016/j.neucom.2025.130291_b16 – volume: 20 start-page: 2526 issue: 10 year: 2008 ident: 10.1016/j.neucom.2025.130291_b19 article-title: Sparse coding via thresholding and local competition in neural circuits publication-title: Neural Comput. doi: 10.1162/neco.2008.03-07-486 – volume: 12 start-page: 241 issue: 3 year: 2001 ident: 10.1016/j.neucom.2025.130291_b3 article-title: Redundancy reduction revisited publication-title: Netw., Comput. Neural Syst. doi: 10.1080/net.12.3.241.253 – year: 2022 ident: 10.1016/j.neucom.2025.130291_b40 – year: 2009 ident: 10.1016/j.neucom.2025.130291_b47 – start-page: 3498 year: 2012 ident: 10.1016/j.neucom.2025.130291_b50 article-title: Cats and dogs – volume: 40 start-page: 1329 issue: 5 year: 2021 ident: 10.1016/j.neucom.2025.130291_b29 article-title: FISTA-net: Learning a fast iterative shrinkage thresholding network for inverse problems in imaging publication-title: IEEE Trans. Med. Imaging doi: 10.1109/TMI.2021.3054167 – year: 2016 ident: 10.1016/j.neucom.2025.130291_b53 – start-page: 129 year: 2024 ident: 10.1016/j.neucom.2025.130291_b62 article-title: LCANets++: Robust audio classification using multi-layer neural networks with lateral competition – volume: 381 start-page: 607 issue: 6583 year: 1996 ident: 10.1016/j.neucom.2025.130291_b4 article-title: Emergence of simple-cell receptive field properties by learning a sparse code for natural images publication-title: Nature doi: 10.1038/381607a0 – volume: 19 issue: 9 year: 2023 ident: 10.1016/j.neucom.2025.130291_b55 article-title: Beyond l1 sparse coding in V1 publication-title: PLoS Comput. Biol. – volume: 68 start-page: 1702 year: 2020 ident: 10.1016/j.neucom.2025.130291_b43 article-title: Model-driven deep learning for MIMO detection publication-title: IEEE Trans. Signal Process. doi: 10.1109/TSP.2020.2976585 – volume: 50 start-page: 65 issue: 1 year: 2009 ident: 10.1016/j.neucom.2025.130291_b23 article-title: Compressed sensing and matrix completion with uniform uncertainty principle publication-title: SIAM Rev. – start-page: 215 year: 2011 ident: 10.1016/j.neucom.2025.130291_b48 article-title: An analysis of single-layer networks in unsupervised feature learning – year: 2011 ident: 10.1016/j.neucom.2025.130291_b10 article-title: Are sparse representations really relevant for image classification? – year: 2017 ident: 10.1016/j.neucom.2025.130291_b12 – ident: 10.1016/j.neucom.2025.130291_b27 – volume: 20 year: 2007 ident: 10.1016/j.neucom.2025.130291_b6 article-title: Sparse deep belief net model for visual area V2 publication-title: Adv. Neural Inf. Process. Syst. – volume: 23 start-page: 1013 issue: 7 year: 2012 ident: 10.1016/j.neucom.2025.130291_b56 article-title: L{1/2} regularization: A thresholding representation theory and a fast solver publication-title: IEEE Trans. Neural Netw. Learn. Syst. doi: 10.1109/TNNLS.2012.2197412 – volume: 17 issue: 1 year: 2021 ident: 10.1016/j.neucom.2025.130291_b59 article-title: Sparse deep predictive coding captures contour integration capabilities of the early visual system publication-title: PLoS Comput. Biol. doi: 10.1371/journal.pcbi.1008629 – volume: 55 start-page: 482 issue: 21 year: 2007 ident: 10.1016/j.neucom.2025.130291_b26 article-title: A generalized forward-backward splitting algorithm for sparse signal recovery publication-title: IEEE Trans. Signal Process. – ident: 10.1016/j.neucom.2025.130291_b21 doi: 10.1145/3546790.3546811 – year: 2018 ident: 10.1016/j.neucom.2025.130291_b14 article-title: Deep sparse coding for invariant multimodal halle berry neurons – year: 2017 ident: 10.1016/j.neucom.2025.130291_b45 – volume: 15 issue: 2 year: 2019 ident: 10.1016/j.neucom.2025.130291_b15 article-title: A hierarchical sparse coding model predicts acoustic feature encoding in both auditory midbrain and cortex publication-title: PLoS Comput. Biol. doi: 10.1371/journal.pcbi.1006766 – year: 2019 ident: 10.1016/j.neucom.2025.130291_b51 – volume: Vol. 4 start-page: IV year: 2007 ident: 10.1016/j.neucom.2025.130291_b35 article-title: Locally competitive algorithms for sparse approximation – start-page: 180 year: 2023 ident: 10.1016/j.neucom.2025.130291_b46 article-title: Generating sparse counterfactual explanations for multivariate time series – volume: 63 start-page: 3165 issue: 12 year: 2015 ident: 10.1016/j.neucom.2025.130291_b34 article-title: Discrete and continuous-time soft-thresholding for dynamic signal recovery publication-title: IEEE Trans. Signal Process. doi: 10.1109/TSP.2015.2420535 – volume: 58 start-page: 267 issue: 1 year: 1996 ident: 10.1016/j.neucom.2025.130291_b36 article-title: Regression Shrinkage and Selection Via the Lasso publication-title: J. R. Stat. Soc. Ser. B Stat. Methodol. doi: 10.1111/j.2517-6161.1996.tb02080.x – start-page: 1492 year: 2017 ident: 10.1016/j.neucom.2025.130291_b54 article-title: Aggregated residual transformations for deep neural networks – volume: 38 start-page: 18 issue: 2 year: 2021 ident: 10.1016/j.neucom.2025.130291_b44 article-title: Algorithm unrolling: Interpretable, efficient deep learning for signal and image processing publication-title: IEEE Signal Process. Mag. doi: 10.1109/MSP.2020.3016905 – year: 2023 ident: 10.1016/j.neucom.2025.130291_b38 – volume: 135 start-page: 158 year: 2021 ident: 10.1016/j.neucom.2025.130291_b8 article-title: Exploitation of image statistics with sparse coding in the case of stereo vision publication-title: Neural Netw. doi: 10.1016/j.neunet.2020.12.016 – ident: 10.1016/j.neucom.2025.130291_b30 doi: 10.1109/CVPR.2018.00196 – start-page: 4340 year: 2016 ident: 10.1016/j.neucom.2025.130291_b41 article-title: Maximal sparsity with deep networks? – volume: 96 start-page: 61 issue: 2 year: 2023 ident: 10.1016/j.neucom.2025.130291_b57 article-title: A reduced half thresholding algorithm publication-title: J. Sci. Comput. doi: 10.1007/s10915-023-02250-1 – ident: 10.1016/j.neucom.2025.130291_b24 doi: 10.1145/1553374.1553463 – volume: 6 start-page: 559 issue: 4 year: 1994 ident: 10.1016/j.neucom.2025.130291_b2 article-title: What is the goal of sensory coding? publication-title: Neural Comput. doi: 10.1162/neco.1994.6.4.559 – volume: 77 start-page: 1 year: 2019 ident: 10.1016/j.neucom.2025.130291_b39 article-title: Machine learning-based warm starting of active set methods in embedded model predictive control publication-title: Eng. Appl. Artif. Intell. doi: 10.1016/j.engappai.2018.09.014 – year: 2024 ident: 10.1016/j.neucom.2025.130291_b61 – start-page: 21232 year: 2022 ident: 10.1016/j.neucom.2025.130291_b18 article-title: LCANets: Lateral competition improves robustness against corruption and attack – volume: 8 start-page: 1607 issue: 3 year: 2015 ident: 10.1016/j.neucom.2025.130291_b58 article-title: A continuous exact ∖ell_0 penalty (CEL0) for least squares regularized problem publication-title: SIAM J. Imaging Sci. doi: 10.1137/151003714 – volume: 15 issue: 6 year: 2019 ident: 10.1016/j.neucom.2025.130291_b7 article-title: Neural correlates of sparse coding and dimensionality reduction publication-title: PLoS Comput. Biol. doi: 10.1371/journal.pcbi.1006908 – volume: 13 start-page: 411 issue: 4–5 year: 2000 ident: 10.1016/j.neucom.2025.130291_b37 article-title: Independent component analysis: algorithms and applications publication-title: Neural Netw. doi: 10.1016/S0893-6080(00)00026-5 – ident: 10.1016/j.neucom.2025.130291_b42 doi: 10.1109/ICCV.2017.627 – volume: 83 start-page: 44 year: 2017 ident: 10.1016/j.neucom.2025.130291_b13 article-title: Medical image classification based on multi-scale non-negative sparse coding publication-title: Artif. Intell. Med. doi: 10.1016/j.artmed.2017.05.006 – ident: 10.1016/j.neucom.2025.130291_b52 doi: 10.1109/CVPR.2017.243 – year: 2019 ident: 10.1016/j.neucom.2025.130291_b32 – volume: 109 start-page: 911 issue: 5 year: 2021 ident: 10.1016/j.neucom.2025.130291_b20 article-title: Advancing neuromorphic computing with loihi: A survey of results and outlook publication-title: Proc. IEEE doi: 10.1109/JPROC.2021.3067593 – volume: 3 start-page: 490 year: 2015 ident: 10.1016/j.neucom.2025.130291_b31 article-title: A survey of sparse representation: algorithms and applications publication-title: IEEE Access doi: 10.1109/ACCESS.2015.2430359 – start-page: 1 year: 2019 ident: 10.1016/j.neucom.2025.130291_b33 article-title: NP-hardness of ℓ0 minimization problems: revision and extension to the non-negative setting – volume: 2 start-page: 183 issue: 1 year: 2009 ident: 10.1016/j.neucom.2025.130291_b25 article-title: A fast iterative shrinkage-thresholding algorithm for linear inverse problems publication-title: SIAM J. Imaging Sci. doi: 10.1137/080716542 – start-page: 238 year: 2020 ident: 10.1016/j.neucom.2025.130291_b17 article-title: Fully trainable and interpretable non-local sparse models for image restoration – start-page: 117 year: 2025 ident: 10.1016/j.neucom.2025.130291_b60 article-title: Improving robustness to model inversion attacks via sparse coding architectures – year: 2016 ident: 10.1016/j.neucom.2025.130291_b11 article-title: Sparse encoding of binocular images for depth inference – volume: 30 start-page: 1487 year: 2020 ident: 10.1016/j.neucom.2025.130291_b28 article-title: AMP-Net: Denoising-based deep unfolding for compressive image sensing publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2020.3044472 – volume: 1 start-page: 217 issue: 01 year: 1961 ident: 10.1016/j.neucom.2025.130291_b1 article-title: Possible principles underlying the transformation of sensory messages publication-title: Sens. Commun. |
| SSID | ssj0017129 |
| Score | 2.4484563 |
| Snippet | The locally competitive algorithm (LCA) can solve sparse coding problems across a wide range of use cases. Recently, convolution-based LCA approaches have been... |
| SourceID | crossref elsevier |
| SourceType | Index Database Publisher |
| StartPage | 130291 |
| SubjectTerms | Computer vision Convolutional sparse coding Locally competitive algorithms |
| Title | WARP-LCA: Efficient convolutional sparse coding with Locally Competitive Algorithm |
| URI | https://dx.doi.org/10.1016/j.neucom.2025.130291 |
| Volume | 640 |
| WOSCitedRecordID | wos001487662200001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVESC databaseName: Elsevier SD Freedom Collection Journals 2021 issn: 0925-2312 databaseCode: AIEXJ dateStart: 19950101 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: https://www.sciencedirect.com omitProxy: false ssIdentifier: ssj0017129 providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3dT9swELdGywMvjDEm2AD5gVdPbdI4Dm8RKl-qKsSH1rco_shUVNKqFNQ_f3e2k7Z0msakvUSRm9iV75fz-fy7O0JOIiEVLHuaYZgk6xiZsyQOOTMa7ImCcxlJmzK_F_f7YjBIbjxt7NmWE4jLUsznyeS_ihraQNgYOvsOcdedQgPcg9DhCmKH618J_kd6e8N6Z9Zx3rUJIvC4H9nlfliMEJnAfhZ56rr2xfZwURs5BYGRZ8goSkc_x1P48WnZhLXpPJQtBuHdDOkTZlvQCK0FdRtWx1LmFSQuzNhGjNUGPEDIqv9zMxrO61blqEIXmC5ywceZuRJ-dyBiq5CWPRVBVPPkvPtsLYTG-SHhQTAyV1Qydymc1tS78zQ8fi_NC3J9cBAsZx24gl9vEmffYdfYM1h5sFELOxukGcRRIhqkmV51B9f1aVPcDlxORv9XqhBLywNcH-v3JsySWXK_Q7b9foKmDgefyAdT7pKPVa0O6lX3Z3JbweKU1qCgK6CgDhTUgYIiKKgHBV0CBa1BsUcezrv3Z5fM19NgChTzjAkVS6EkVgAouEzCqBUUAeYnSlq8JTVYdirPW0KHSudchSLHSmZ52xTcqDDWMvxCGuW4NPuEcllgXqF22DaiU2j42rko8IRYqwJuOgeEVVOUTVzalKziEz5mbkoznNLMTekBiat5zLzp50y6DET_xze__vOb38jWAqWHpDGbvpgjsqleZ8Pn6bHHyC_HqoAS |
| linkProvider | Elsevier |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=WARP-LCA%3A+Efficient+convolutional+sparse+coding+with+Locally+Competitive+Algorithm&rft.jtitle=Neurocomputing+%28Amsterdam%29&rft.au=Kasenbacher%2C+Geoffrey&rft.au=Ehret%2C+Felix&rft.au=Ecke%2C+Gerrit&rft.au=Otte%2C+Sebastian&rft.date=2025-08-01&rft.pub=Elsevier+B.V&rft.issn=0925-2312&rft.volume=640&rft_id=info:doi/10.1016%2Fj.neucom.2025.130291&rft.externalDocID=S0925231225009634 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0925-2312&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0925-2312&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0925-2312&client=summon |