{"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/efficient-adaptation-of-large-vision-1","title":"Efficient Adaptation of Large Vision Transformer via Adapter Re-Composing","arxiv_id":"2310.06234","date":"2023-10-10","proceeding":"NeurIPS 2023 11","authors":["Wei Dong","Dawei Yan","Zhijun Lin","Peng Wang"],"abstract":"The advent of high-capacity pre-trained models has revolutionized problem-solving in computer vision, shifting the focus from training task-specific models to adapting pre-trained models. Consequently, effectively adapting large pre-trained models to downstream tasks in an efficient manner has become a prominent research area. Existing solutions primarily concentrate on designing lightweight adapters and their interaction with pre-trained models, with the goal of minimizing the number of parameters requiring updates. In this study, we propose a novel Adapter Re-Composing (ARC) strategy that addresses efficient pre-trained model adaptation from a fresh perspective. Our approach considers the reusability of adaptation parameters and introduces a parameter-sharing scheme. Specifically, we leverage symmetric down-/up-projections to construct bottleneck operations, which are shared across layers. By learning low-dimensional re-scaling coefficients, we can effectively re-compose layer-adaptive adapters. This parameter-sharing strategy in adapter design allows us to significantly reduce the number of new parameters while maintaining satisfactory performance, thereby offering a promising approach to compress the adaptation cost. We conduct experiments on 24 downstream image classification tasks using various Vision Transformer variants to evaluate our method. The results demonstrate that our approach achieves compelling transfer learning performance with a reduced parameter count. Our code is available at \\href{https://github.com/DavidYanAnDe/ARC}{https://github.com/DavidYanAnDe/ARC}.","url_abs":"https://arxiv.org/abs/2310.06234v2","url_pdf":"https://arxiv.org/pdf/2310.06234v2.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":"efficient-adaptation-of-large-vision-1","repo_url":"https://github.com/davidyanande/arc","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"arc","task_name":"ARC"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"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":"adapter","method_name":"Adapter"},{"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":"focus","method_name":"Focus"},{"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"},{"method_slug":"vision-transformer","method_name":"Vision Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2310.06234","atlas_url":"https://app.syntology.ai/?focus=2310.06234","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.06234"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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":"deterministic:regex_extraction","url":"https://github.com/DavidYanAnDe/ARC","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/davidyanande/arc","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":4,"ran_fixture":1,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":7,"ran":6,"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":"a0901740b20e9382","entry":"ARC_adapter","repo":"davidyanande/arc","repo_kind":"official","path":"Model/ARC_ViT.py","file_url":"https://github.com/davidyanande/arc/blob/HEAD/Model/ARC_ViT.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a0901740b20e9382"}},{"code_sha256_prefix":"a2d01766b58dccb1","entry":"default_flist_reader","repo":"DavidYanAnDe/ARC","repo_kind":"official","path":"Data_process/VTAB_loader.py","file_url":"https://github.com/DavidYanAnDe/ARC/blob/HEAD/Data_process/VTAB_loader.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a2d01766b58dccb1"}},{"code_sha256_prefix":"ac269a0e4b8d946e","entry":"default_loader","repo":"DavidYanAnDe/ARC","repo_kind":"official","path":"Data_process/VTAB_loader.py","file_url":"https://github.com/DavidYanAnDe/ARC/blob/HEAD/Data_process/VTAB_loader.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ac269a0e4b8d946e"}},{"code_sha256_prefix":"c5363b397021e658","entry":"get_data","repo":"DavidYanAnDe/ARC","repo_kind":"official","path":"Data_process/VTAB_loader.py","file_url":"https://github.com/DavidYanAnDe/ARC/blob/HEAD/Data_process/VTAB_loader.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c5363b397021e658"}},{"code_sha256_prefix":"993ae96666b00cb5","entry":"window_partition","repo":"DavidYanAnDe/ARC","repo_kind":"official","path":"Model/ARC_swin_b.py","file_url":"https://github.com/DavidYanAnDe/ARC/blob/HEAD/Model/ARC_swin_b.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"993ae96666b00cb5"}},{"code_sha256_prefix":"609922bd93c75117","entry":"window_reverse","repo":"DavidYanAnDe/ARC","repo_kind":"official","path":"Model/ARC_swin_b.py","file_url":"https://github.com/DavidYanAnDe/ARC/blob/HEAD/Model/ARC_swin_b.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"609922bd93c75117"}},{"code_sha256_prefix":"3c241ecfe3749a6d","entry":"simple_accuracy","repo":"DavidYanAnDe/ARC","repo_kind":"official","path":"FGVC_ARC_train.py","file_url":"https://github.com/DavidYanAnDe/ARC/blob/HEAD/FGVC_ARC_train.py","link_basis":"plan_row","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":"3c241ecfe3749a6d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}