{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T03:16:54Z","timestamp":1783048614914,"version":"3.54.6"},"reference-count":87,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100018542","name":"Natural Science Foundation of Sichuan Province","doi-asserted-by":"publisher","award":["2025ZNSFSC1464"],"award-info":[{"award-number":["2025ZNSFSC1464"]}],"id":[{"id":"10.13039\/501100018542","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62376209"],"award-info":[{"award-number":["62376209"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100012542","name":"Sichuan Provincial Science and Technology Support Program","doi-asserted-by":"publisher","award":["2026NSFSC0430"],"award-info":[{"award-number":["2026NSFSC0430"]}],"id":[{"id":"10.13039\/100012542","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.neucom.2026.134145","type":"journal-article","created":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T06:41:54Z","timestamp":1780382514000},"page":"134145","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Modular knowledge distillation for MIM pre-trained models"],"prefix":"10.1016","volume":"697","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2870-3974","authenticated-orcid":false,"given":"Shiwei","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4906-4569","authenticated-orcid":false,"given":"Jiale","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Ke","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4839-0234","authenticated-orcid":false,"given":"Dongyang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guiduo","family":"Duan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2026.134145_bib0005","article-title":"Beit: BERT pre-training of image transformers","author":"Bao","year":"2022","journal-title":"Int. Conf. Learn. Represent."},{"key":"10.1016\/j.neucom.2026.134145_bib0010","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","article-title":"Masked autoencoders are scalable vision learners","author":"He","year":"2022"},{"key":"10.1016\/j.neucom.2026.134145_bib0015","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"9653","article-title":"Simmim: a simple framework for masked image modeling","author":"Xie","year":"2022"},{"key":"10.1016\/j.neucom.2026.134145_bib0020","first-page":"611","article-title":"An image is worth 16x16 words: transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"Int. Conf. Learn. Represent."},{"key":"10.1016\/j.neucom.2026.134145_bib0025","first-page":"8344","article-title":"Hivit: hierarchical vision transformer meets masked image modeling","author":"Zhang","year":"2023","journal-title":"Int. Conf. Learn. Represent."},{"issue":"1","key":"10.1016\/j.neucom.2026.134145_bib0030","doi-asserted-by":"crossref","first-page":"208","DOI":"10.1007\/s11263-023-01852-4","article-title":"Context autoencoder for self-supervised representation learning","volume":"132","author":"Chen","year":"2024","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.neucom.2026.134145_bib0035","author":"Peng"},{"key":"10.1016\/j.neucom.2026.134145_bib0040","series-title":"International Conference on Machine Learning","article-title":"Data2vec: a general framework for self-supervised learning in speech, vision and language","author":"Baevski","year":"2022"},{"key":"10.1016\/j.neucom.2026.134145_bib0045","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"14668","article-title":"Masked feature prediction for self-supervised visual pre-training","author":"Wei","year":"2022"},{"key":"10.1016\/j.neucom.2026.134145_bib0050","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.neucom.2026.134145_bib0055","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"12259","article-title":"Levit: a vision transformer in convnet\u2019s clothing for faster inference","author":"Graham","year":"2021"},{"key":"10.1016\/j.neucom.2026.134145_bib0060","series-title":"International Conference on Learning Representations","article-title":"MobileViT: light-weight, general-purpose, and mobile-friendly vision transformer","author":"Mehta","year":"2022"},{"key":"10.1016\/j.neucom.2026.134145_bib0065","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"14420","article-title":"Efficientvit: memory efficient vision transformer with cascaded group attention","author":"Liu","year":"2023"},{"key":"10.1016\/j.neucom.2026.134145_bib0070","series-title":"International Conference on Machine Learning","article-title":"Training data-efficient image transformers & distillation through attention","author":"Touvron","year":"2021"},{"key":"10.1016\/j.neucom.2026.134145_bib0075","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"12052","article-title":"Dearkd: data-efficient early knowledge distillation for vision transformers","author":"Chen","year":"2022"},{"key":"10.1016\/j.neucom.2026.134145_bib0080","doi-asserted-by":"crossref","first-page":"9164","DOI":"10.52202\/068431-0666","article-title":"Learning efficient vision transformers via fine-grained manifold distillation","volume":"35","author":"Hao","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134145_bib0085","author":"Liu"},{"key":"10.1016\/j.neucom.2026.134145_bib0090","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","article-title":"Masked autoencoders enable efficient knowledge distillers","author":"Bai","year":"2023"},{"issue":"9","key":"10.1016\/j.neucom.2026.134145_bib0095","doi-asserted-by":"crossref","first-page":"8779","DOI":"10.1109\/TCSVT.2024.3393474","article-title":"Generic-to-specific distillation of masked autoencoders","volume":"34","author":"Huang","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.neucom.2026.134145_bib0100","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","article-title":"Tinymim: an empirical study of distilling Mim pre-trained models","author":"Ren","year":"2023"},{"key":"10.1016\/j.neucom.2026.134145_bib0105","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"6825","article-title":"Integrally migrating pre-trained transformer encoder-decoders for visual object detection","author":"Liu","year":"2023"},{"key":"10.1016\/j.neucom.2026.134145_bib0110","series-title":"European Conference on Computer Vision","first-page":"280","article-title":"Exploring plain vision transformer backbones for object detection","author":"Li","year":"2022"},{"key":"10.1016\/j.neucom.2026.134145_bib0115","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"12104","article-title":"Scaling vision transformers","author":"Zhai","year":"2022"},{"key":"10.1016\/j.neucom.2026.134145_bib0120","series-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","first-page":"9676","article-title":"MAP: unleashing hybrid Mamba-transformer vision backbone\u2019s potential with masked autoregressive pretraining","author":"Liu","year":"2025"},{"key":"10.1016\/j.neucom.2026.134145_bib0125","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"1314","article-title":"Searching for mobilenetv3","author":"Howard","year":"2019"},{"key":"10.1016\/j.neucom.2026.134145_bib0130","first-page":"1","article-title":"Deep compression: compressing deep neural networks with pruning, trained quantization and huffman coding","author":"Han","year":"2016","journal-title":"Int. Conf. Learn. Represent."},{"issue":"241","key":"10.1016\/j.neucom.2026.134145_bib0135","first-page":"1","article-title":"Sparsity in deep learning: pruning and growth for efficient inference and training in neural networks","volume":"22","author":"Hoefler","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.neucom.2026.134145_bib0140","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"16176","article-title":"Sparsemae: sparse training meets masked autoencoders","author":"Zhou","year":"2023"},{"key":"10.1016\/j.neucom.2026.134145_bib0145","series-title":"European Conference on Computer Vision","first-page":"68","article-title":"Tinyvit: fast pretraining distillation for small vision transformers","author":"Wu","year":"2022"},{"key":"10.1016\/j.neucom.2026.134145_bib0150","series-title":"Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"10.1016\/j.neucom.2026.134145_bib0155","author":"Zhong"},{"key":"10.1016\/j.neucom.2026.134145_bib0160","series-title":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","first-page":"10391","article-title":"Revisiting token dropping strategy in efficient BERT pretraining","author":"Zhong","year":"2023"},{"key":"10.1016\/j.neucom.2026.134145_bib0165","series-title":"International Conference on Machine Learning","first-page":"8821","article-title":"Zero-shot text-to-image generation","author":"Ramesh","year":"2021"},{"key":"10.1016\/j.neucom.2026.134145_bib0170","series-title":"IEEE Computer Society Conference on Computer Vision and Pattern Recognition","article-title":"Histograms of oriented gradients for human detection","author":"Dalal","year":"2005"},{"key":"10.1016\/j.neucom.2026.134145_bib0175","first-page":"4639","article-title":"Image BERT pre-training with online tokenizer","author":"Zhou","year":"2022","journal-title":"Int. Conf. Learn. Represent."},{"key":"10.1016\/j.neucom.2026.134145_bib0180","series-title":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"1","article-title":"Masked image pretraining on language assisted representation","author":"Hou","year":"2025"},{"key":"10.1016\/j.neucom.2026.134145_bib0185","series-title":"International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.neucom.2026.134145_bib0190","doi-asserted-by":"crossref","first-page":"19997","DOI":"10.52202\/068431-1454","article-title":"Green hierarchical vision transformer for masked image modeling","volume":"35","author":"Huang","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134145_bib0195","series-title":"International Conference on Machine Learning","first-page":"35624","article-title":"A closer look at self-supervised lightweight vision transformers","author":"Wang","year":"2023"},{"key":"10.1016\/j.neucom.2026.134145_bib0200","series-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","first-page":"25230","article-title":"Closest neighbors are harmful for lightweight masked auto-encoders","author":"Meng","year":"2025"},{"key":"10.1016\/j.neucom.2026.134145_bib0205","article-title":"Rethinking patch dependence for masked autoencoders","author":"Fu","year":"2025","journal-title":"Trans. Mach. Learn. Res.","ISSN":"https:\/\/id.crossref.org\/issn\/2835-8856","issn-type":"print"},{"key":"10.1016\/j.neucom.2026.134145_bib0210","author":"Hinton"},{"issue":"6","key":"10.1016\/j.neucom.2026.134145_bib0215","doi-asserted-by":"crossref","first-page":"1789","DOI":"10.1007\/s11263-021-01453-z","article-title":"Knowledge distillation: a survey","volume":"129","author":"Gou","year":"2021","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.neucom.2026.134145_bib0220","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","article-title":"A comprehensive overhaul of feature distillation","author":"Heo","year":"2019"},{"key":"10.1016\/j.neucom.2026.134145_bib0225","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence, 33","first-page":"3779","article-title":"Knowledge transfer via distillation of activation boundaries formed by hidden neurons","author":"Heo","year":"2019"},{"key":"10.1016\/j.neucom.2026.134145_bib0230","series-title":"Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021","article-title":"MiniLMv2: multi-head self-attention relation distillation for compressing pretrained transformers","author":"Wang","year":"2021"},{"key":"10.1016\/j.neucom.2026.134145_bib0235","doi-asserted-by":"crossref","first-page":"4262","DOI":"10.1109\/TMM.2022.3192663","article-title":"CDFKD-MFS: collaborative data-free knowledge distillation via multi-level feature sharing","volume":"24","author":"Hao","year":"2022","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.neucom.2026.134145_bib0240","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"2604","article-title":"Structured knowledge distillation for semantic segmentation","author":"Liu","year":"2019"},{"key":"10.1016\/j.neucom.2026.134145_bib0245","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"5311","article-title":"Channel-wise knowledge distillation for dense prediction","author":"Shu","year":"2021"},{"key":"10.1016\/j.neucom.2026.134145_bib0250","series-title":"Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","article-title":"Learning from multiple teacher networks","author":"You","year":"2017"},{"key":"10.1016\/j.neucom.2026.134145_bib0255","doi-asserted-by":"crossref","first-page":"7901","DOI":"10.1109\/TMM.2024.3372833","article-title":"Reciprocal teacher-student learning via forward and feedback knowledge distillation","volume":"26","author":"Gou","year":"2024","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.neucom.2026.134145_bib0260","doi-asserted-by":"crossref","first-page":"1526","DOI":"10.1109\/TMM.2024.3521772","article-title":"Progressive knowledge distillation from different levels of teachers for online action detection","volume":"27","author":"Moniruzzaman","year":"2025","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.neucom.2026.134145_bib0265","doi-asserted-by":"crossref","first-page":"2083","DOI":"10.1109\/TMM.2024.3521793","article-title":"Adaptive knowledge distillation with attention-based multi-modal fusion for robust dim object detection","volume":"27","author":"Lan","year":"2025","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.neucom.2026.134145_bib0270","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"4643","article-title":"Focal and global knowledge distillation for detectors","author":"Yang","year":"2022"},{"key":"10.1016\/j.neucom.2026.134145_bib0275","doi-asserted-by":"crossref","first-page":"495","DOI":"10.1109\/TIP.2025.3648880","article-title":"Turbidity\u2013similarity decoupling: feature-consistent mutual learning for underwater salient object detection","volume":"35","author":"Zhou","year":"2026","journal-title":"IEEE Trans. Image Process."},{"issue":"3","key":"10.1016\/j.neucom.2026.134145_bib0280","doi-asserted-by":"crossref","first-page":"3989","DOI":"10.1109\/TCSVT.2025.3617769","article-title":"RCNet: dual-network resonance collaboration via mutual learning for RGB-D road defect detection","volume":"36","author":"Zhou","year":"2026","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.neucom.2026.134145_bib0285","article-title":"Dependency then compression: global dependency network with three-stage knowledge transfer for visible-infrared transmission line detection","author":"Zhou","year":"2026","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.neucom.2026.134145_bib0290","first-page":"3156","article-title":"Contrastive representation distillation","author":"Tian","year":"2020","journal-title":"Int. Conf. Learn. Represent."},{"key":"10.1016\/j.neucom.2026.134145_bib0295","author":"Romero"},{"key":"10.1016\/j.neucom.2026.134145_bib0300","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"4320","article-title":"Deep mutual learning","author":"Zhang","year":"2018"},{"key":"10.1016\/j.neucom.2026.134145_bib0305","doi-asserted-by":"crossref","first-page":"3027","DOI":"10.1109\/TIP.2023.3275538","article-title":"WaveNet: wavelet network with knowledge distillation for RGB-T salient object detection","volume":"32","author":"Zhou","year":"2023","journal-title":"IEEE Trans. Image Process."},{"issue":"4","key":"10.1016\/j.neucom.2026.134145_bib0310","doi-asserted-by":"crossref","first-page":"3222","DOI":"10.1109\/TCSVT.2024.3508058","article-title":"MDNet: Mamba-effective diffusion-distillation network for RGB-thermal urban dense prediction","volume":"35","author":"Zhou","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.neucom.2026.134145_bib0315","first-page":"1","article-title":"ETDNet: efficient transformer-based detection network for surface defect detection","volume":"72","author":"Zhou","year":"2023","journal-title":"IEEE Trans. Instrum. Meas."},{"issue":"10","key":"10.1016\/j.neucom.2026.134145_bib0320","doi-asserted-by":"crossref","first-page":"18287","DOI":"10.1109\/TNNLS.2025.3575088","article-title":"Multiattentive perception and multilayer transfer network using knowledge distillation for RGB-D indoor scene parsing","volume":"36","author":"Zhou","year":"2025","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"8","key":"10.1016\/j.neucom.2026.134145_bib0325","doi-asserted-by":"crossref","first-page":"4140","DOI":"10.1109\/TCSI.2024.3521933","article-title":"Knowledge distillation and contrastive learning for detecting visible-infrared transmission lines using separated stagger registration network","volume":"72","author":"Zhou","year":"2025","journal-title":"IEEE Trans. Circuits Syst. I Regul. Pap."},{"key":"10.1016\/j.neucom.2026.134145_bib0330","article-title":"Adaptive adjustment multi-teacher distillation network for visible-infrared transmission line detection","author":"Zhou","year":"2026","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"2","key":"10.1016\/j.neucom.2026.134145_bib0335","doi-asserted-by":"crossref","first-page":"1429","DOI":"10.1109\/JOE.2025.3538928","article-title":"Toward real-world applicability: lightweight underwater acoustic localization model through knowledge distillation","volume":"50","author":"Hu","year":"2025","journal-title":"IEEE J. Ocean. Eng."},{"key":"10.1016\/j.neucom.2026.134145_bib0340","first-page":"1","article-title":"Union-domain knowledge distillation for underwater acoustic target recognition","volume":"63","author":"Chu","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.neucom.2026.134145_bib0345","first-page":"1","article-title":"HCL-net: heterogeneous collaborative learning for lightweight remote sensing image segmentation","volume":"64","author":"Xie","year":"2026","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.neucom.2026.134145_bib0350","first-page":"1","article-title":"Adapt, generate, and supervise: geometry-aware diffusion-guided SAM framework for remote sensing semantic segmentation","volume":"64","author":"Zhou","year":"2026","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.neucom.2026.134145_bib0355","article-title":"Graph attention guidance network with knowledge distillation for semantic segmentation of remote sensing images","volume":"61","author":"Zhou","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.neucom.2026.134145_bib0360","first-page":"4163","article-title":"Tinybert: distilling BERT for natural language understanding","author":"Jiao","year":"2020","journal-title":"Int. Conf. Learn. Represent."},{"key":"10.1016\/j.neucom.2026.134145_bib0365","series-title":"European Conference on Computer Vision","first-page":"379","article-title":"The role of masking for efficient supervised knowledge distillation of vision transformers","author":"Son","year":"2024"},{"key":"10.1016\/j.neucom.2026.134145_bib0370","series-title":"European Conference on Artificial Intelligence","article-title":"Mim-hd: making smaller masked autoencoder better with efficient distillation","author":"Zhang","year":"2024"},{"issue":"10","key":"10.1016\/j.neucom.2026.134145_bib0375","doi-asserted-by":"crossref","first-page":"9681","DOI":"10.1109\/TCSVT.2025.3565616","article-title":"Dfmc: feature-driven data-free knowledge distillation","volume":"35","author":"Zhang","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.neucom.2026.134145_bib0380","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"26617","article-title":"Promptkd: unsupervised prompt distillation for vision-language models","author":"Li","year":"2024"},{"key":"10.1016\/j.neucom.2026.134145_bib0385","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"9163","article-title":"Variational information distillation for knowledge transfer","author":"Ahn","year":"2019"},{"key":"10.1016\/j.neucom.2026.134145_bib0390","series-title":"European Conference on Computer Vision","article-title":"Microsoft COCO: common objects in context","author":"Lin","year":"2014"},{"issue":"3","key":"10.1016\/j.neucom.2026.134145_bib0395","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.neucom.2026.134145_bib0400","first-page":"4061","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2019","journal-title":"Int. Conf. Learn. Represent."},{"key":"10.1016\/j.neucom.2026.134145_bib0405","first-page":"5213","article-title":"Distilling object detectors with feature richness","volume":"34","author":"Zhixing","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134145_bib0410","series-title":"Proceedings of the European Conference on Computer Vision","first-page":"418","article-title":"Unified perceptual parsing for scene understanding","author":"Xiao","year":"2018"},{"key":"10.1016\/j.neucom.2026.134145_bib0415","series-title":"International Conference on Machine Learning","article-title":"Self-supervised models are good teaching assistants for vision transformers","author":"Wu","year":"2022"},{"key":"10.1016\/j.neucom.2026.134145_bib0420","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"9650","article-title":"Emerging properties in self-supervised vision transformers","author":"Caron","year":"2021"},{"issue":"7","key":"10.1016\/j.neucom.2026.134145_bib0425","doi-asserted-by":"crossref","first-page":"3918","DOI":"10.1007\/s11263-024-02327-w","article-title":"An experimental study on exploring strong lightweight vision transformers via masked image modeling pre-training","volume":"133","author":"Gao","year":"2025","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.neucom.2026.134145_bib0430","series-title":"The Twelfth International Conference on Learning Representations","article-title":"Boosting vanilla lightweight vision transformers via re-parameterization","author":"Tan","year":"2024"},{"key":"10.1016\/j.neucom.2026.134145_bib0435","series-title":"Proceedings of the European Conference on Computer Vision","first-page":"709","article-title":"Visual prompt tuning","author":"Jia","year":"2022"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226015432?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226015432?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T02:35:47Z","timestamp":1783046147000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226015432"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":87,"alternative-id":["S0925231226015432"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134145","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Modular knowledge distillation for MIM pre-trained models","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134145","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"134145"}}