{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/minivit-compressing-vision-transformers-with","title":"MiniViT: Compressing Vision Transformers with Weight Multiplexing","arxiv_id":"2204.07154","date":"2022-04-14","proceeding":"CVPR 2022 1","authors":["Jinnian Zhang","Houwen Peng","Kan Wu","Mengchen Liu","Bin Xiao","Jianlong Fu","Lu Yuan"],"abstract":"Vision Transformer (ViT) models have recently drawn much attention in computer vision due to their high model capability. However, ViT models suffer from huge number of parameters, restricting their applicability on devices with limited memory. To alleviate this problem, we propose MiniViT, a new compression framework, which achieves parameter reduction in vision transformers while retaining the same performance. The central idea of MiniViT is to multiplex the weights of consecutive transformer blocks. More specifically, we make the weights shared across layers, while imposing a transformation on the weights to increase diversity. Weight distillation over self-attention is also applied to transfer knowledge from large-scale ViT models to weight-multiplexed compact models. Comprehensive experiments demonstrate the efficacy of MiniViT, showing that it can reduce the size of the pre-trained Swin-B transformer by 48\\%, while achieving an increase of 1.0\\% in Top-1 accuracy on ImageNet. Moreover, using a single-layer of parameters, MiniViT is able to compress DeiT-B by 9.7 times from 86M to 9M parameters, without seriously compromising the performance. Finally, we verify the transferability of MiniViT by reporting its performance on downstream benchmarks. Code and models are available at here.","url_abs":"https://arxiv.org/abs/2204.07154v1","url_pdf":"https://arxiv.org/pdf/2204.07154v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"minivit-compressing-vision-transformers-with","repo_url":"https://github.com/microsoft/cream","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"minivit-compressing-vision-transformers-with","repo_url":"https://github.com/microsoft/AutoML","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"image-classification","task_name":"Image Classification"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"Mini-Swin-B@384","rank_in_archive_order":220,"of":1060,"metrics":{"GFLOPs":"98.8","Number of params":"47M","Top 1 Accuracy":"85.5%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2204.07154","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.07154"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/microsoft/cream","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/microsoft/AutoML","reach":null}],"summary":{"unverified":4},"by_repo_kind":{"listed":{"samples":4,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"2cbff10d73eb7a6c","entry":"BasicLayer","repo":"microsoft/AutoML","repo_kind":"listed","path":"MiniViT/Mini-Swin/models/swin_transformer_minivit.py","file_url":"https://github.com/microsoft/AutoML/blob/HEAD/MiniViT/Mini-Swin/models/swin_transformer_minivit.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2cbff10d73eb7a6c"}},{"code_sha256_prefix":"4f8688d9e12ea3d2","entry":"SwinTransformerBlock","repo":"microsoft/AutoML","repo_kind":"listed","path":"MiniViT/Mini-Swin/models/swin_transformer_minivit.py","file_url":"https://github.com/microsoft/AutoML/blob/HEAD/MiniViT/Mini-Swin/models/swin_transformer_minivit.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4f8688d9e12ea3d2"}},{"code_sha256_prefix":"9d3f653a351ddc1b","entry":"SwinTransformerMiniViT","repo":"microsoft/AutoML","repo_kind":"listed","path":"MiniViT/Mini-Swin/models/swin_transformer_minivit.py","file_url":"https://github.com/microsoft/AutoML/blob/HEAD/MiniViT/Mini-Swin/models/swin_transformer_minivit.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9d3f653a351ddc1b"}},{"code_sha256_prefix":"3095ac15907de9ab","entry":"WindowAttention","repo":"microsoft/AutoML","repo_kind":"listed","path":"MiniViT/Mini-Swin/models/swin_transformer_minivit.py","file_url":"https://github.com/microsoft/AutoML/blob/HEAD/MiniViT/Mini-Swin/models/swin_transformer_minivit.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3095ac15907de9ab"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}