{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T11:24:06Z","timestamp":1772796246957,"version":"3.50.1"},"reference-count":56,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2023,5,28]],"date-time":"2023-05-28T00:00:00Z","timestamp":1685232000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Natural Science Foundation of China","award":["62172193"],"award-info":[{"award-number":["62172193"]}]},{"name":"National Natural Science Foundation of China","award":["62272051"],"award-info":[{"award-number":["62272051"]}]},{"name":"National Natural Science Foundation of China","award":["KM201910009014"],"award-info":[{"award-number":["KM201910009014"]}]},{"name":"General Project of Science and Technology Plan of Beijing Municipal Commission of Education","award":["62172193"],"award-info":[{"award-number":["62172193"]}]},{"name":"General Project of Science and Technology Plan of Beijing Municipal Commission of Education","award":["62272051"],"award-info":[{"award-number":["62272051"]}]},{"name":"General Project of Science and Technology Plan of Beijing Municipal Commission of Education","award":["KM201910009014"],"award-info":[{"award-number":["KM201910009014"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Deep unrolling networks (DUNs) have emerged as a promising approach for solving compressed sensing (CS) problems due to their superior explainability, speed, and performance compared to classical deep network models. However, the CS performance in terms of efficiency and accuracy remains a principal challenge for approaching further improvements. In this paper, we propose a novel deep unrolling model, SALSA-Net, to solve the image CS problem. The network architecture of SALSA-Net is inspired by unrolling and truncating the split augmented Lagrangian shrinkage algorithm (SALSA) which is used to solve sparsity-induced CS reconstruction problems. SALSA-Net inherits the interpretability of the SALSA algorithm while incorporating the learning ability and fast reconstruction speed of deep neural networks. By converting the SALSA algorithm into a deep network structure, SALSA-Net consists of a gradient update module, a threshold denoising module, and an auxiliary update module. All parameters, including the shrinkage thresholds and gradient steps, are optimized through end-to-end learning and are subject to forward constraints to ensure faster convergence. Furthermore, we introduce learned sampling to replace traditional sampling methods so that the sampling matrix can better preserve the feature information of the original signal and improve sampling efficiency. Experimental results demonstrate that SALSA-Net achieves significant reconstruction performance compared to state-of-the-art methods while inheriting the advantages of explainable recovery and high speed from the DUNs paradigm.<\/jats:p>","DOI":"10.3390\/s23115142","type":"journal-article","created":{"date-parts":[[2023,5,28]],"date-time":"2023-05-28T15:29:52Z","timestamp":1685287792000},"page":"5142","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["SALSA-Net: Explainable Deep Unrolling Networks for Compressed Sensing"],"prefix":"10.3390","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8583-2804","authenticated-orcid":false,"given":"Heping","family":"Song","sequence":"first","affiliation":[{"name":"School of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang 212013, China"},{"name":"Jiangsu Engineering Research Center of Big Data Ubiquitous Perception and Intelligent Agriculture Applications, Zhenjiang 212013, China"}]},{"given":"Qifeng","family":"Ding","sequence":"additional","affiliation":[{"name":"School of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang 212013, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5907-5836","authenticated-orcid":false,"given":"Jingyao","family":"Gong","sequence":"additional","affiliation":[{"name":"School of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang 212013, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8836-1382","authenticated-orcid":false,"given":"Hongying","family":"Meng","sequence":"additional","affiliation":[{"name":"Electronic and Electrical Engineering Department, Brunel University London, Uxbridge UB8 3PH, UK"}]},{"given":"Yuping","family":"Lai","sequence":"additional","affiliation":[{"name":"School of Cyberspace Security, Beijing University of Posts and Telecommunications, Beijing 100876, China"}]}],"member":"1968","published-online":{"date-parts":[[2023,5,28]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1289","DOI":"10.1109\/TIT.2006.871582","article-title":"Compressed sensing","volume":"52","author":"Donoho","year":"2006","journal-title":"IEEE Trans. Inf. Theory"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"489","DOI":"10.1109\/TIT.2005.862083","article-title":"Robust uncertainty principles: Exact signal reconstruction from highly incomplete frequency information","volume":"52","author":"Candes","year":"2006","journal-title":"IEEE Trans. Inf. Theory"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"5406","DOI":"10.1109\/TIT.2006.885507","article-title":"Near-optimal signal recovery from random projections: Universal encoding strategies?","volume":"52","author":"Candes","year":"2006","journal-title":"IEEE Trans. Inf. Theory"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"736","DOI":"10.1109\/LGRS.2014.2360457","article-title":"Compressed sensing of a remote sensing image based on the priors of the reference image","volume":"12","author":"Wang","year":"2015","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1109\/MSP.2007.914730","article-title":"Single-pixel imaging via compressive sampling","volume":"25","author":"Duarte","year":"2008","journal-title":"IEEE Signal Process. Mag."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1109\/MSP.2019.2951469","article-title":"Transform learning for magnetic resonance image reconstruction: From model-based learning to building neural networks","volume":"37","author":"Wen","year":"2020","journal-title":"IEEE Signal Process. Mag."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"2177","DOI":"10.1109\/TII.2012.2189222","article-title":"Compressed sensing signal and data acquisition in wireless sensor networks and internet of things","volume":"9","author":"Li","year":"2012","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1006","DOI":"10.1109\/JPROC.2009.2037526","article-title":"Sparsity and compressed sensing in radar imaging","volume":"98","author":"Potter","year":"2010","journal-title":"Proc. IEEE"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1016\/j.acha.2012.08.003","article-title":"Spectral compressive sensing","volume":"35","author":"Duarte","year":"2013","journal-title":"Appl. Comput. Harmon. Anal."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1031","DOI":"10.1109\/JPROC.2010.2044470","article-title":"Sparse representation for computer vision and pattern recognition","volume":"98","author":"Wright","year":"2010","journal-title":"Proc. IEEE"},{"key":"ref_11","unstructured":"Gan, L. (2007, January 1\u20134). Block Compressed Sensing of Natural Images. Proceedings of the International Conference on Digital Signal Processing (ICDSP), Cardiff, UK."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.acha.2014.02.001","article-title":"The restricted isometry property for random block diagonal matrices","volume":"38","author":"Eftekhari","year":"2015","journal-title":"Appl. Comput. Harmon. Anal."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1137\/060657704","article-title":"From Sparse Solutions of Systems of Equations to Sparse Modeling of Signals and Images","volume":"51","author":"Bruckstein","year":"2009","journal-title":"Siam Rev."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"948","DOI":"10.1109\/JPROC.2010.2044010","article-title":"Computational methods for sparse solution of linear inverse problems","volume":"98","author":"Tropp","year":"2010","journal-title":"Proc. IEEE"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"756","DOI":"10.1093\/nsr\/nwx069","article-title":"Sparse recovery: From vectors to tensors","volume":"5","author":"Wang","year":"2018","journal-title":"Natl. Sci. Rev."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"139303","DOI":"10.1007\/s11432-020-3126-7","article-title":"Sparse signal reconstruction via generalized two-stage thresholding","volume":"65","author":"Song","year":"2022","journal-title":"Sci. China Inf. Sci."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"18914","DOI":"10.1073\/pnas.0909892106","article-title":"Message-passing algorithms for compressed sensing","volume":"106","author":"Donoho","year":"2009","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1561\/2400000003","article-title":"Proximal Algorithms","volume":"1","author":"Parikh","year":"2014","journal-title":"Found. Trends Optim."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"507","DOI":"10.1007\/s10589-013-9576-1","article-title":"An efficient augmented Lagrangian method with applications to total variation minimization","volume":"56","author":"Li","year":"2013","journal-title":"Comput. Optim. Appl."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"301","DOI":"10.1016\/j.acha.2008.07.002","article-title":"CoSaMP: Iterative signal recovery from incomplete and inaccurate samples","volume":"26","author":"Needell","year":"2009","journal-title":"Appl. Comput. Harmon. Anal."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"2230","DOI":"10.1109\/TIT.2009.2016006","article-title":"Subspace pursuit for compressive sensing signal reconstruction","volume":"55","author":"Dai","year":"2009","journal-title":"IEEE Trans. Inf. Theory"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1016\/j.acha.2009.04.002","article-title":"Iterative hard thresholding for compressed sensing","volume":"27","author":"Blumensath","year":"2009","journal-title":"Appl. Comput. Harmon. Anal."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1137\/080716542","article-title":"A fast iterative shrinkage-thresholding algorithm for linear inverse problems","volume":"2","author":"Beck","year":"2009","journal-title":"SIAM J. Imaging Sci."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1137\/090756855","article-title":"NESTA: A fast and accurate first-order method for sparse recovery","volume":"4","author":"Becker","year":"2011","journal-title":"SIAM J. Imaging Sci."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"2345","DOI":"10.1109\/TIP.2010.2047910","article-title":"Fast image recovery using variable splitting and constrained optimization","volume":"19","author":"Afonso","year":"2010","journal-title":"IEEE Trans. Image Process."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"681","DOI":"10.1109\/TIP.2010.2076294","article-title":"An augmented Lagrangian approach to the constrained optimization formulation of imaging inverse problems","volume":"20","author":"Afonso","year":"2010","journal-title":"IEEE Trans. Image Process."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1109\/MSP.2022.3208394","article-title":"Physics-inspired compressive sensing: Beyond deep unrolling","volume":"40","author":"Zhang","year":"2023","journal-title":"IEEE Signal Process. Mag."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1109\/MSP.2020.3016905","article-title":"Algorithm unrolling: Interpretable, efficient deep learning for signal and image processing","volume":"38","author":"Monga","year":"2021","journal-title":"IEEE Signal Process. Mag."},{"key":"ref_29","first-page":"1","article-title":"Learning to optimize: A primer and a benchmark","volume":"23","author":"Chen","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref_30","unstructured":"Mousavi, A., Patel, A.B., and Baraniuk, R.G. (October, January 29). A deep learning approach to structured signal recovery. Proceedings of the 53rd Annual Allerton Conference on Communication, Control, and Computing (Allerton), Monticello, IL, USA."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Kulkarni, K., Lohit, S., Turaga, P., Kerviche, R., and Ashok, A. (2016, January 27\u201330). Reconnet: Non-iterative reconstruction of images from compressively sensed measurements. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.55"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"2080","DOI":"10.1109\/TIP.2007.901238","article-title":"Image denoising by sparse 3-D transform-domain collaborative filtering","volume":"16","author":"Dabov","year":"2007","journal-title":"IEEE Trans. Image Process."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"483","DOI":"10.1016\/j.neucom.2019.05.006","article-title":"DR2-Net: Deep residual reconstruction network for image compressive sensing","volume":"359","author":"Yao","year":"2019","journal-title":"Neurocomputing"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Shi, W., Jiang, F., Zhang, S., and Zhao, D. (2017, January 10\u201314). Deep networks for compressed image sensing. Proceedings of the IEEE International Conference on Multimedia and Expo (ICME), Hong Kong, China.","DOI":"10.1109\/ICME.2017.8019428"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"3236","DOI":"10.1109\/TMM.2020.2973862","article-title":"Learning non-locally regularized compressed sensing network with half-quadratic splitting","volume":"22","author":"Sun","year":"2020","journal-title":"IEEE Trans. Multimed."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"5412","DOI":"10.1109\/TIP.2022.3195319","article-title":"Content-aware scalable deep compressed sensing","volume":"31","author":"Chen","year":"2022","journal-title":"IEEE Trans. Image Process."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"2627","DOI":"10.1109\/TMM.2020.3014561","article-title":"Multi-Channel Deep Networks for Block-Based Image Compressive Sensing","volume":"23","author":"Zhou","year":"2021","journal-title":"IEEE Trans. Multimed."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"6066","DOI":"10.1109\/TIP.2021.3091834","article-title":"Coast: Controllable arbitrary-sampling network for compressive sensing","volume":"30","author":"You","year":"2021","journal-title":"IEEE Trans. Image Process."},{"key":"ref_39","unstructured":"Gregor, K., and LeCun, Y. (2010, January 21\u201324). Learning fast approximations of sparse coding. Proceedings of the International Conference on Machine Learning (ICML), Haifa, Israel."},{"key":"ref_40","unstructured":"Chen, X., Liu, J., Wang, Z., and Yin, W. (2018, January 2\u20138). Theoretical linear convergence of unfolded ISTA and its practical weights and thresholds. Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), Montreal, QB, Canada."},{"key":"ref_41","unstructured":"Liu, J., Chen, X., Wang, Z., and Yin, W. (2019, January 6\u20139). ALISTA: Analytic weights are as good as learned weights in LISTA. Proceedings of the International Conference on Learning Representations (ICLR), New Orleans, LA, USA."},{"key":"ref_42","unstructured":"Wu, K., Guo, Y., Li, Z., and Zhang, C. (1, January 26). Sparse coding with gated learned ISTA. Proceedings of the International Conference on Learning Representations (ICLR), Addis Ababa, Ethiopia."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Li, Y., Kong, L., Shang, F., Liu, Y., Liu, H., and Lin, Z. (2021, January 2\u20139). Learned extragradient ISTA with interpretable residual structures for sparse coding. Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), Online.","DOI":"10.1609\/aaai.v35i10.17032"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"9222","DOI":"10.1109\/TPAMI.2021.3125041","article-title":"Ada-LISTA: Learned Solvers Adaptive to Varying Models","volume":"44","author":"Aberdam","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_45","first-page":"3226","article-title":"Hybrid ISTA: Unfolding ISTA with convergence guarantees using free-form deep neural networks","volume":"43","author":"Zheng","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Zhang, J., and Ghanem, B. (2018, January 18\u201323). ISTA-Net: Interpretable optimization-inspired deep network for image compressive sensing. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00196"},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"You, D., Xie, J., and Zhang, J. (2021, January 5\u20139). ISTA-NET++: Flexible deep unfolding network for compressive sensing. Proceedings of the IEEE International Conference on Multimedia and Expo (ICME), Shenzhen, China.","DOI":"10.1109\/ICME51207.2021.9428249"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"1329","DOI":"10.1109\/TMI.2021.3054167","article-title":"FISTA-Net: Learning a Fast Iterative Shrinkage Thresholding Network for Inverse Problems in Imaging","volume":"40","author":"Xiang","year":"2021","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"521","DOI":"10.1109\/TPAMI.2018.2883941","article-title":"ADMM-CSNet: A deep learning approach for image compressive sensing","volume":"42","author":"Yang","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"1088","DOI":"10.1109\/JSTSP.2020.2998402","article-title":"RARE: Image reconstruction using deep priors learned without groundtruth","volume":"14","author":"Liu","year":"2020","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"1487","DOI":"10.1109\/TIP.2020.3044472","article-title":"AMP-Net: Denoising-based deep unfolding for compressive image sensing","volume":"30","author":"Zhang","year":"2021","journal-title":"IEEE Trans. Image Process."},{"key":"ref_52","doi-asserted-by":"crossref","unstructured":"Chen, J., Sun, Y., Liu, Q., and Huang, R. (2020, January 23\u201328). Learning memory augmented cascading network for compressed sensing of images. Proceedings of the European Conference Computer Vision (ECCV), Glasgow, UK.","DOI":"10.1007\/978-3-030-58542-6_31"},{"key":"ref_53","unstructured":"Ye, D., Ni, Z., Wang, H., Zhang, J., Wang, S., and Kwong, S. (2021). CSformer: Bridging Convolution and Transformer for Compressive Sensing. arXiv."},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"6991","DOI":"10.1109\/TIP.2022.3217365","article-title":"TransCS: A Transformer-Based Hybrid Architecture for Image Compressed Sensing","volume":"31","author":"Shen","year":"2022","journal-title":"IEEE Trans. Image Process."},{"key":"ref_55","doi-asserted-by":"crossref","unstructured":"Bevilacqua, M., Roumy, A., Guillemot, C., and Alberi-Morel, M.L. (2012, January 3\u20137). Low-complexity single-image super-resolution based on nonnegative neighbor embedding. Proceedings of the British Machine Vision Conference (BMVC), Surrey, UK.","DOI":"10.5244\/C.26.135"},{"key":"ref_56","doi-asserted-by":"crossref","first-page":"9482","DOI":"10.1109\/TIP.2020.3023629","article-title":"Dual-path attention network for compressed sensing image reconstruction","volume":"29","author":"Sun","year":"2020","journal-title":"IEEE Trans. Image Process."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/11\/5142\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T19:43:48Z","timestamp":1760125428000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/11\/5142"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,28]]},"references-count":56,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2023,6]]}},"alternative-id":["s23115142"],"URL":"https:\/\/doi.org\/10.3390\/s23115142","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,5,28]]}}}