{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T13:36:50Z","timestamp":1780925810621,"version":"3.54.1"},"reference-count":71,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62192783"],"award-info":[{"award-number":["62192783"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276128"],"award-info":[{"award-number":["62276128"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62406140"],"award-info":[{"award-number":["62406140"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Young Elite Scientists Sponsorship Program by China Association for Science and Technology","award":["2023QNRC001"],"award-info":[{"award-number":["2023QNRC001"]}]},{"name":"Key Research and Development Program of Jiangsu Province","award":["BE2023019"],"award-info":[{"award-number":["BE2023019"]}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20221441"],"award-info":[{"award-number":["BK20221441"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20241200"],"award-info":[{"award-number":["BK20241200"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1109\/tpami.2025.3554560","type":"journal-article","created":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T07:28:13Z","timestamp":1742974093000},"page":"5806-5817","source":"Crossref","is-referenced-by-count":5,"title":["ONNXPruner: ONNX-Based General Model Pruning Adapter"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8360-4947","authenticated-orcid":false,"given":"Dongdong","family":"Ren","sequence":"first","affiliation":[{"name":"School of Electronic Science and Engineering, Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0935-7124","authenticated-orcid":false,"given":"Wenbin","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory for Novel Software Technology and School of Intelligence Science and Technology, Nanjing University, Suzhou Campus, Suzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8445-4330","authenticated-orcid":false,"given":"Tianyu","family":"Ding","sequence":"additional","affiliation":[{"name":"Applied Sciences Group, Microsoft Corporation, Redmond, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0961-0441","authenticated-orcid":false,"given":"Lei","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computing and Information Technology, University of Wollongong, Wollongong, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2644-4457","authenticated-orcid":false,"given":"Qi","family":"Fan","sequence":"additional","affiliation":[{"name":"State Key Laboratory for Novel Software Technology and School of Intelligence Science and Technology, Nanjing University, Suzhou Campus, Suzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8504-455X","authenticated-orcid":false,"given":"Jing","family":"Huo","sequence":"additional","affiliation":[{"name":"State Key Laboratory for Novel Software Technology and School of Intelligence Science and Technology, Nanjing University, Suzhou Campus, Suzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7181-8278","authenticated-orcid":false,"given":"Hongbing","family":"Pan","sequence":"additional","affiliation":[{"name":"School of Electronic Science and Engineering, Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2488-1813","authenticated-orcid":false,"given":"Yang","family":"Gao","sequence":"additional","affiliation":[{"name":"State Key Laboratory for Novel Software Technology and School of Intelligence Science and Technology, Nanjing University, Suzhou Campus, Suzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01544"},{"key":"ref2","first-page":"1135","article-title":"Learning both weights and connections for efficient neural network","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Han"},{"key":"ref3","first-page":"7021","article-title":"Group fisher pruning for practical network compression","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Liu"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00525"},{"key":"ref5","article-title":"NEMO: A toolkit for building AI applications using neural modules","author":"Kuchaiev","year":"2019"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1983"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858232"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3089687"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01467"},{"key":"ref10","first-page":"13986","article-title":"Directional pruning of deep neural networks","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Chao"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3334614"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00198"},{"key":"ref13","first-page":"57","article-title":"Orthant based proximal stochastic gradient method for $l_1$l1-regularized optimization","volume-title":"Proc. Mach. Learn. Knowl. Discov. Databases - Eur. Conf.","author":"Chen"},{"key":"ref14","article-title":"Neural network compression via sparse optimization","author":"Chen","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.298"},{"key":"ref16","first-page":"1","article-title":"Pruning filters for efficient convnets","volume-title":"Proc. 5th Int. Conf. Learn. Representations","author":"Li"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00447"},{"key":"ref18","first-page":"6682","article-title":"Proving the lottery ticket hypothesis: Pruning is all you need","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Malach"},{"key":"ref19","first-page":"19637","article-title":"Only train once: A one-shot neural network training and pruning framework","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref20","first-page":"1","article-title":"OTOV2: Automatic, generic, user-friendly","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Chen"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01198"},{"key":"ref22","article-title":"Onnx","year":"2019"},{"key":"ref23","first-page":"2130","article-title":"Gate decorator: Global filter pruning method for accelerating deep convolutional neural networks","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"You"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/309"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00160"},{"key":"ref26","first-page":"1106","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Krizhevsky"},{"key":"ref27","article-title":"SqueezeNet: Alexnet-level accuracy with 50\u00d7 fewer parameters and! 0.5 mb model size","author":"Iandola","year":"2016"},{"key":"ref28","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref32","article-title":"An image is worth 16\u2009\u00d7\u200916 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref33","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref34","article-title":"Analysis of failures and risks in deep learning model converters: A case study in the onnx ecosystem","author":"Jajal","year":"2023"},{"key":"ref35","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Paszke"},{"key":"ref36","first-page":"265","article-title":"Tensorflow: A system for large-scale machine learning","volume-title":"Proc. 12th USENIX Symp. Operating Syst. Des. Implementation","author":"Abadi"},{"key":"ref37","article-title":"Mxnet: A flexible and efficient machine learning library for heterogeneous distributed systems","author":"Chen","year":"2015"},{"key":"ref38","first-page":"578","article-title":"TVM: An automated end-to-end optimizing compiler for deep learning","volume-title":"Proc. 13th USENIX Symp. Operating Syst. Des. Implementation","author":"Chen"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/LES.2021.3087707"},{"key":"ref40","article-title":"Openvino documentation","year":"2021"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2874634"},{"key":"ref42","first-page":"4857","article-title":"Learning to prune deep neural networks via layer-wise optimal brain surgeon","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Dong"},{"key":"ref43","article-title":"A signal propagation perspective for pruning neural networks at initialization","author":"Lee","year":"2019"},{"key":"ref44","article-title":"Lookahead: A far-sighted alternative of magnitude-based pruning","author":"Park","year":"2020"},{"key":"ref45","first-page":"1","article-title":"SNIP: Single-shot network pruning based on connection sensitivity","volume-title":"Proc. 7th Int. Conf. Learn. Representations","author":"Lee"},{"key":"ref46","first-page":"1","article-title":"Picking winning tickets before training by preserving gradient flow","volume-title":"Proc. 8th Int. Conf. Learn. Representations","author":"Wang"},{"key":"ref47","first-page":"1","article-title":"Progressive skeletonization: Trimming more fat from a network at initialization","volume-title":"Proc. 9th Int. Conf. Learn. Representations","author":"Sanyal"},{"key":"ref48","first-page":"3259","article-title":"Linear mode connectivity and the lottery ticket hypothesis","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Frankle"},{"key":"ref49","first-page":"1","article-title":"Dynamic model pruning with feedback","volume-title":"Proc. 8th Int. Conf. Learn. Representations","author":"Lin"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2023.3319594"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01004"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.155"},{"key":"ref54","article-title":"Structurally prune anything: Any architecture, any framework, any time","author":"Wang","year":"2024"},{"key":"ref55","article-title":"Onnx-runtime environment","year":"2021"},{"key":"ref56","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126343"},{"key":"ref60","first-page":"8","article-title":"A framework for few-shot language model evaluation","volume":"10","author":"Gao","year":"2021","journal-title":"Version V0. 0.1. Sep."},{"key":"ref61","article-title":"Boolq: Exploring the surprising difficulty of natural yes\/no questions","author":"Clark","year":"2019"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6239"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1472"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3474381"},{"key":"ref65","article-title":"Think you have solved question answering? Try arc, the AI2 reasoning challenge","author":"Clark","year":"2018"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1260"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01152"},{"key":"ref68","article-title":"Neural pruning via growing regularization","author":"Wang","year":"2020"},{"key":"ref69","article-title":"Why is the state of neural network pruning so confusing? On the fairness, comparison setup, and trainability in network pruning","author":"Wang","year":"2023"},{"key":"ref70","article-title":"Trainability preserving neural structured pruning","author":"Wang","year":"2022"},{"key":"ref71","article-title":"Stanford alpaca: An instruction-following LLaMA model","author":"Taori","year":"2023"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11026037\/10938408.pdf?arnumber=10938408","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,6]],"date-time":"2025-06-06T17:42:33Z","timestamp":1749231753000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10938408\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":71,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3554560","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7]]}}}