{"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/supervised-fine-tuning-in-turn-improves","title":"Supervised Fine-tuning in turn Improves Visual Foundation Models","arxiv_id":"2401.10222","date":"2024-01-18","proceeding":null,"authors":["Xiaohu Jiang","Yixiao Ge","Yuying Ge","Dachuan Shi","Chun Yuan","Ying Shan"],"abstract":"Image-text training like CLIP has dominated the pretraining of vision foundation models in recent years. Subsequent efforts have been made to introduce region-level visual learning into CLIP's pretraining but face scalability challenges due to the lack of large-scale region-level datasets. Drawing inspiration from supervised fine-tuning (SFT) in natural language processing such as instruction tuning, we explore the potential of fine-grained SFT in enhancing the generation of vision foundation models after their pretraining. Thus a two-stage method ViSFT (Vision SFT) is proposed to unleash the fine-grained knowledge of vision foundation models. In ViSFT, the vision foundation model is enhanced by performing visual joint learning on some in-domain tasks and then tested on out-of-domain benchmarks. With updating using ViSFT on 8 V100 GPUs in less than 2 days, a vision transformer with over 4.4B parameters shows improvements across various out-of-domain benchmarks including vision and vision-linguistic scenarios.","url_abs":"https://arxiv.org/abs/2401.10222v2","url_pdf":"https://arxiv.org/pdf/2401.10222v2.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":"supervised-fine-tuning-in-turn-improves","repo_url":"https://github.com/tencentarc/visft","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"clip","method_name":"CLIP"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"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":"residual-connection","method_name":"Residual Connection"},{"method_slug":"sft","method_name":"SFT"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"vision-transformer","method_name":"Vision Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2401.10222","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.10222"}},"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/tencentarc/visft","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":6,"unverified":6},"by_repo_kind":{"official":{"samples":12,"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":"a7f346bb7a69c595","entry":"accuracy","repo":"tencentarc/visft","repo_kind":"official","path":"mmf/models/visft/caption_decoder.py","file_url":"https://github.com/tencentarc/visft/blob/HEAD/mmf/models/visft/caption_decoder.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a7f346bb7a69c595"}},{"code_sha256_prefix":"a3619d3754ec34c3","entry":"get_abs_pos","repo":"tencentarc/visft","repo_kind":"official","path":"mmf/models/visft/eva_vit_g.py","file_url":"https://github.com/tencentarc/visft/blob/HEAD/mmf/models/visft/eva_vit_g.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a3619d3754ec34c3"}},{"code_sha256_prefix":"cd9b01650559d0be","entry":"get_norm","repo":"tencentarc/visft","repo_kind":"official","path":"mmf/models/visft/misc.py","file_url":"https://github.com/tencentarc/visft/blob/HEAD/mmf/models/visft/misc.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cd9b01650559d0be"}},{"code_sha256_prefix":"9dbedd9018e1a9ad","entry":"get_uncertain_point_coords_with_randomness","repo":"tencentarc/visft","repo_kind":"official","path":"mmf/models/visft/point_sampler.py","file_url":"https://github.com/tencentarc/visft/blob/HEAD/mmf/models/visft/point_sampler.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9dbedd9018e1a9ad"}},{"code_sha256_prefix":"f9525ce415e0a0cf","entry":"get_uncertain_point_coords_with_randomness_and_valid_mask","repo":"tencentarc/visft","repo_kind":"official","path":"mmf/models/visft/point_sampler.py","file_url":"https://github.com/tencentarc/visft/blob/HEAD/mmf/models/visft/point_sampler.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f9525ce415e0a0cf"}},{"code_sha256_prefix":"e8c3f53b24248086","entry":"nested_tensor_from_tensor_list","repo":"tencentarc/visft","repo_kind":"official","path":"mmf/models/visft/misc.py","file_url":"https://github.com/tencentarc/visft/blob/HEAD/mmf/models/visft/misc.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e8c3f53b24248086"}},{"code_sha256_prefix":"bc2cb481a75c370d","entry":"batch_dice_loss","repo":"tencentarc/visft","repo_kind":"official","path":"mmf/models/visft/segment_matcher.py","file_url":"https://github.com/tencentarc/visft/blob/HEAD/mmf/models/visft/segment_matcher.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bc2cb481a75c370d"}},{"code_sha256_prefix":"1edd24985036b0bf","entry":"batch_sigmoid_ce_loss","repo":"tencentarc/visft","repo_kind":"official","path":"mmf/models/visft/segment_matcher.py","file_url":"https://github.com/tencentarc/visft/blob/HEAD/mmf/models/visft/segment_matcher.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1edd24985036b0bf"}},{"code_sha256_prefix":"2dcb8123d89bb1ff","entry":"calculate_uncertainty","repo":"tencentarc/visft","repo_kind":"official","path":"mmf/models/visft/segment_criterion.py","file_url":"https://github.com/tencentarc/visft/blob/HEAD/mmf/models/visft/segment_criterion.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2dcb8123d89bb1ff"}},{"code_sha256_prefix":"89f75e54ff128be0","entry":"dice_loss","repo":"tencentarc/visft","repo_kind":"official","path":"mmf/models/visft/segment_criterion.py","file_url":"https://github.com/tencentarc/visft/blob/HEAD/mmf/models/visft/segment_criterion.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"89f75e54ff128be0"}},{"code_sha256_prefix":"90469906eb7f6e8f","entry":"point_sample","repo":"tencentarc/visft","repo_kind":"official","path":"mmf/models/visft/point_sampler.py","file_url":"https://github.com/tencentarc/visft/blob/HEAD/mmf/models/visft/point_sampler.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"90469906eb7f6e8f"}},{"code_sha256_prefix":"d0c61e8dba511aa3","entry":"sigmoid_ce_loss","repo":"tencentarc/visft","repo_kind":"official","path":"mmf/models/visft/segment_criterion.py","file_url":"https://github.com/tencentarc/visft/blob/HEAD/mmf/models/visft/segment_criterion.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d0c61e8dba511aa3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}