{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,24]],"date-time":"2026-05-24T00:09:35Z","timestamp":1779581375121,"version":"3.53.1"},"reference-count":63,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/100019132","name":"Tokyo Polytechnic University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100019132","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Applied Soft Computing"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1016\/j.asoc.2026.115151","type":"journal-article","created":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T15:46:35Z","timestamp":1774885595000},"page":"115151","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Efficient vision transformers via patch selective soft-masked attention and knowledge distillation"],"prefix":"10.1016","volume":"196","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-6094-223X","authenticated-orcid":false,"given":"Abdelfattah","family":"Toulaoui","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2426-8063","authenticated-orcid":false,"given":"Hamza","family":"Khalfi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5039-2458","authenticated-orcid":false,"given":"Imad","family":"Hafidi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.asoc.2026.115151_bib0005","series-title":"Advances in Neural Information Processing Systems","article-title":"Attention is all you need","volume":"vol. 30","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.asoc.2026.115151_bib0010","author":"Dosovitskiy"},{"key":"10.1016\/j.asoc.2026.115151_bib0015","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2023.106643","article-title":"Genevit: gene vision transformer with improved deepinsight for cancer classification","volume":"155","author":"Gokhale","year":"2023","journal-title":"Comput. Biol. Med."},{"key":"10.1016\/j.asoc.2026.115151_bib0020","doi-asserted-by":"crossref","DOI":"10.19139\/soic-2310-5070-2539","article-title":"Vision transformers for breast cancer mammographic image classification","author":"Aniq","year":"2025","journal-title":"Stat. Optim. Inf. Comput."},{"key":"10.1016\/j.asoc.2026.115151_bib0025","series-title":"2024 IEEE International Conference on Image Processing (ICIP)","first-page":"3017","article-title":"A needle in a (medical) haystack: detecting a biopsy needle in ultrasound images using vision transformers","author":"Wijata","year":"2024"},{"issue":"9","key":"10.1016\/j.asoc.2026.115151_bib0030","doi-asserted-by":"crossref","first-page":"5521","DOI":"10.3390\/app13095521","article-title":"Comparing vision transformers and convolutional neural networks for image classification: a literature review","volume":"13","author":"Maur\u00edcio","year":"2023","journal-title":"Appl. Sci."},{"key":"10.1016\/j.asoc.2026.115151_bib0035","series-title":"LSG Attention: Extrapolation of Pretrained Transformers to Long Sequences","first-page":"443","author":"Condevaux","year":"2023"},{"key":"10.1016\/j.asoc.2026.115151_bib0040","series-title":"2023 10th International Conference on Wireless Networks and Mobile Communications (WINCOM)","first-page":"1","article-title":"A comprehensive survey on efficient transformers","author":"Elouargui","year":"2023"},{"key":"10.1016\/j.asoc.2026.115151_bib0045","author":"Hinton"},{"key":"10.1016\/j.asoc.2026.115151_bib0050","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.128896","article-title":"Doa-vit: dual-objective affine vision transformer for data insufficiency","volume":"615","author":"Ren","year":"2025","journal-title":"Neurocomputing"},{"issue":"5","key":"10.1016\/j.asoc.2026.115151_bib0055","doi-asserted-by":"crossref","first-page":"3910","DOI":"10.1109\/TPAMI.2024.3355890","article-title":"Pruning self-attentions into convolutional layers in single path","volume":"46","author":"He","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.asoc.2026.115151_bib0060","doi-asserted-by":"crossref","DOI":"10.1016\/j.imavis.2024.105239","article-title":"Simultaneous image patch attention and pruning for patch selective transformer","author":"Kim","year":"2024","journal-title":"Image Vis. Comput."},{"key":"10.1016\/j.asoc.2026.115151_bib0065","series-title":"International Conference on Machine Learning","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","author":"Touvron","year":"2021"},{"key":"10.1016\/j.asoc.2026.115151_bib0070","series-title":"2025 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","first-page":"693","article-title":"Optimising vision transformer performance on limited datasets: a multi-gradient approach","author":"Ali","year":"2025"},{"key":"10.1016\/j.asoc.2026.115151_bib0075","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.131670","article-title":"A lightweight convolution and vision transformer integrated model with multi-scale self-attention mechanism","volume":"658","author":"Zhang","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.asoc.2026.115151_bib0080","series-title":"Advances in Neural Information Processing Systems","first-page":"13937","article-title":"Dynamicvit: efficient vision transformers with dynamic token sparsification","volume":"vol. 34","author":"Rao","year":"2021"},{"key":"10.1016\/j.asoc.2026.115151_bib0085","series-title":"International Conference on Learning Representations","article-title":"Not all patches are what you need: expediting vision transformers via token reorganizations","author":"Liang","year":"2022"},{"key":"10.1016\/j.asoc.2026.115151_bib0090","series-title":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"12299","article-title":"AdaViT: adaptive vision transformers for efficient image recognition","author":"Meng","year":"2022"},{"key":"10.1016\/j.asoc.2026.115151_bib0095","series-title":"2021 IEEE\/CVF International Conference on Computer Vision (ICCV)","article-title":"Scalable vision transformers with hierarchical pooling","author":"Pan","year":"2021"},{"key":"10.1016\/j.asoc.2026.115151_bib0100","series-title":"2021 IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"9992","article-title":"Swin transformer: hierarchical vision transformer using shifted windows","author":"Liu","year":"2021"},{"key":"10.1016\/j.asoc.2026.115151_bib0105","series-title":"2021 IEEE\/CVF International Conference on Computer Vision (ICCV)","article-title":"Pyramid vision transformer: a versatile backbone for dense prediction without convolutions","author":"Wang","year":"2021"},{"key":"10.1016\/j.asoc.2026.115151_bib0110","series-title":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"12155","article-title":"Patch slimming for efficient vision transformers","author":"Tang","year":"2022"},{"key":"10.1016\/j.asoc.2026.115151_bib0115","series-title":"2021 IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"22","article-title":"Cvt: introducing convolutions to vision transformers","author":"Wu","year":"2021"},{"issue":"11","key":"10.1016\/j.asoc.2026.115151_bib0120","doi-asserted-by":"crossref","DOI":"10.1088\/1742-5468\/ac9830","article-title":"ConViT: improving vision transformers with soft convolutional inductive biases*","volume":"2022","author":"d\u2019Ascoli","year":"2022","journal-title":"J. Stat. Mech.: Theory Exp."},{"key":"10.1016\/j.asoc.2026.115151_bib0125","series-title":"2021 IEEE\/CVF International Conference on Computer Vision (ICCV)","article-title":"LeViT: a vision transformer in convnet\u2019s clothing for faster inference","author":"Graham","year":"2021"},{"key":"10.1016\/j.asoc.2026.115151_bib0130","first-page":"3965","article-title":"Coatnet: marrying convolution and attention for all data sizes","volume":"34","author":"Dai","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.asoc.2026.115151_bib0135","first-page":"12934","article-title":"Efficientformer: vision transformers at mobilenet speed","volume":"35","author":"Li","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.asoc.2026.115151_bib0140","series-title":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"12042","article-title":"Dearkd: data-efficient early knowledge distillation for vision transformers","author":"Chen","year":"2022"},{"key":"10.1016\/j.asoc.2026.115151_bib0145","doi-asserted-by":"crossref","first-page":"3578","DOI":"10.1109\/TIP.2025.3573474","article-title":"Ckd: contrastive knowledge distillation from a sample-wise perspective","volume":"34","author":"Zhu","year":"2025","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.asoc.2026.115151_bib0150","series-title":"TinyViT: Fast Pretraining Distillation for Small Vision Transformers","first-page":"68","author":"Wu","year":"2022"},{"key":"10.1016\/j.asoc.2026.115151_bib0155","series-title":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"12135","article-title":"Minivit: compressing vision transformers with weight multiplexing","author":"Zhang","year":"2022"},{"key":"10.1016\/j.asoc.2026.115151_bib0160","author":"Tian"},{"key":"10.1016\/j.asoc.2026.115151_bib0165","series-title":"Advances in Neural Information Processing Systems (NeurIPS)","article-title":"FlashAttention: fast and memory-efficient exact attention with IO-awareness","author":"Dao","year":"2022"},{"key":"10.1016\/j.asoc.2026.115151_bib0170","series-title":"International Conference on Learning Representations (ICLR)","article-title":"Flashattention-2: faster attention with better parallelism and work partitioning","author":"Dao","year":"2024"},{"issue":"3","key":"10.1016\/j.asoc.2026.115151_bib0175","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","article-title":"ImageNet large scale visual recognition challenge","volume":"115","author":"Russakovsky","year":"2015","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.asoc.2026.115151_bib0180","series-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","article-title":"Designing network design spaces","author":"Radosavovic","year":"2020"},{"key":"10.1016\/j.asoc.2026.115151_bib0185","series-title":"NIPS 2017 Workshop on Autodiff","article-title":"Automatic differentiation in PyTorch","author":"Paszke","year":"2017"},{"key":"10.1016\/j.asoc.2026.115151_bib0190","series-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","article-title":"Randaugment: practical automated data augmentation with a reduced search space","author":"Cubuk","year":"2020"},{"key":"10.1016\/j.asoc.2026.115151_bib0195","series-title":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"2818","article-title":"Rethinking the inception architecture for computer vision","author":"Szegedy","year":"2016"},{"issue":"7","key":"10.1016\/j.asoc.2026.115151_bib0200","first-page":"13001","article-title":"Random erasing data augmentation","volume":"34","author":"Zhong","year":"2020","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"10.1016\/j.asoc.2026.115151_bib0205","author":"Zhang"},{"key":"10.1016\/j.asoc.2026.115151_bib0210","series-title":"2019 IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"6022","article-title":"Cutmix: regularization strategy to train strong classifiers with localizable features","author":"Yun","year":"2019"},{"key":"10.1016\/j.asoc.2026.115151_bib0215","unstructured":"R. Wightman, Pytorch image models, 2019, 10.5281\/zenodo.4414861, https:\/\/github.com\/rwightman\/pytorch-image-models"},{"key":"10.1016\/j.asoc.2026.115151_bib0220","author":"Loshchilov"},{"key":"10.1016\/j.asoc.2026.115151_bib0225","series-title":"29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2 (ASPLOS \u201924)","article-title":"PyTorch 2: faster machine learning through dynamic Python bytecode transformation and graph compilation","author":"Ansel","year":"2024"},{"key":"10.1016\/j.asoc.2026.115151_bib0230","series-title":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","article-title":"A-vit: adaptive tokens for efficient vision transformer","author":"Yin","year":"2022"},{"key":"10.1016\/j.asoc.2026.115151_bib0235","series-title":"2021 IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"377","article-title":"Scalable vision transformers with hierarchical pooling","author":"Pan","year":"2021"},{"key":"10.1016\/j.asoc.2026.115151_bib0240","series-title":"International Conference on Learning Representations","article-title":"Unified visual transformer compression","author":"Yu","year":"2022"},{"key":"10.1016\/j.asoc.2026.115151_bib0245","series-title":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"24355","article-title":"X-pruner: explainable pruning for vision transformers","author":"Yu","year":"2023"},{"issue":"3","key":"10.1016\/j.asoc.2026.115151_bib0250","first-page":"3143","article-title":"Width & depth pruning for vision transformers","volume":"36","author":"Yu","year":"2022","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"10.1016\/j.asoc.2026.115151_bib0255","series-title":"Proceedings of the 37th International Conference on Machine Learning","first-page":"3690","article-title":"PoWER-BERT: accelerating BERT inference via progressive word-vector elimination","volume":"vol. 119","author":"Goyal","year":"2020"},{"key":"10.1016\/j.asoc.2026.115151_bib0260","series-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems","article-title":"Scop: scientific control for reliable neural network pruning","author":"Tang","year":"2020"},{"issue":"1","key":"10.1016\/j.asoc.2026.115151_bib0265","first-page":"1","article-title":"Statistical comparisons of classifiers over multiple data sets","volume":"7","author":"Dem\u0161ar","year":"2006","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.asoc.2026.115151_bib0270","series-title":"Individual Comparisons by Ranking Methods","first-page":"196","author":"Wilcoxon","year":"1992"},{"issue":"2","key":"10.1016\/j.asoc.2026.115151_bib0275","first-page":"65","article-title":"A simple sequentially rejective multiple test procedure","volume":"6","author":"Holm","year":"1979","journal-title":"Scand. J. Stat."},{"issue":"1","key":"10.1016\/j.asoc.2026.115151_bib0280","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1016\/j.cviu.2005.09.012","article-title":"Learning generative visual models from few training exles: an incremental Bayesian approach tested on 101 object categories","volume":"106","author":"Fei-Fei","year":"2007","journal-title":"Comput. Vis. Image Underst."},{"key":"10.1016\/j.asoc.2026.115151_bib0285","series-title":"2008 Sixth Indian Conference on Computer Vision, Graphics & Image Processing","first-page":"722","article-title":"Automated flower classification over a large number of classes","author":"Nilsback","year":"2008"},{"key":"10.1016\/j.asoc.2026.115151_bib0290","series-title":"The caltech-ucsd birds-200-2011 dataset","author":"Wah","year":"2011"},{"issue":"3","key":"10.1016\/j.asoc.2026.115151_bib0295","doi-asserted-by":"crossref","first-page":"302","DOI":"10.1007\/s11263-018-1140-0","article-title":"Semantic understanding of scenes through the ade20k dataset","volume":"127","author":"Zhou","year":"2019","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.asoc.2026.115151_bib0300","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","article-title":"Scene parsing through ade20k dataset","author":"Zhou","year":"2017"},{"key":"10.1016\/j.asoc.2026.115151_bib0305","series-title":"European Conference on Computer Vision","article-title":"Unified perceptual parsing for scene understanding","author":"Xiao","year":"2018"},{"key":"10.1016\/j.asoc.2026.115151_bib0310","article-title":"Faster r-Cnn: towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"2","key":"10.1016\/j.asoc.2026.115151_bib0315","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","article-title":"The pascal visual object classes (VOC) challenge","volume":"88","author":"Everingham","year":"2010","journal-title":"Int. J. Comput. Vis."}],"container-title":["Applied Soft Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1568494626005995?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1568494626005995?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,23]],"date-time":"2026-05-23T23:39:38Z","timestamp":1779579578000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1568494626005995"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":63,"alternative-id":["S1568494626005995"],"URL":"https:\/\/doi.org\/10.1016\/j.asoc.2026.115151","relation":{},"ISSN":["1568-4946"],"issn-type":[{"value":"1568-4946","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Efficient vision transformers via patch selective soft-masked attention and knowledge distillation","name":"articletitle","label":"Article Title"},{"value":"Applied Soft Computing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.asoc.2026.115151","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"115151"}}