{"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/classification-done-right-for-vision-language","title":"Classification Done Right for Vision-Language Pre-Training","arxiv_id":"2411.03313","date":"2024-11-05","proceeding":null,"authors":["Zilong Huang","Qinghao Ye","Bingyi Kang","Jiashi Feng","Haoqi Fan"],"abstract":"We introduce SuperClass, a super simple classification method for vision-language pre-training on image-text data. Unlike its contrastive counterpart CLIP who contrast with a text encoder, SuperClass directly utilizes tokenized raw text as supervised classification labels, without the need for additional text filtering or selection. Due to the absence of the text encoding as contrastive target, SuperClass does not require a text encoder and does not need to maintain a large batch size as CLIP does. SuperClass demonstrated superior performance on various downstream tasks, including classic computer vision benchmarks and vision language downstream tasks. We further explored the scaling behavior of SuperClass on model size, training length, or data size, and reported encouraging results and comparisons to CLIP. https://github.com/x-cls/superclass","url_abs":"https://arxiv.org/abs/2411.03313v2","url_pdf":"https://arxiv.org/pdf/2411.03313v2.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":"classification-done-right-for-vision-language","repo_url":"https://github.com/x-cls/superclass","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"}],"methods":[{"method_slug":"clip","method_name":"CLIP"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2411.03313","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.03313"}},"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/x-cls/superclass","reach":null}],"summary":{"ran":7,"ran_draft_wrong":3,"unverified":8},"by_repo_kind":{"official":{"samples":18,"ran":10,"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":"785f7419f700fb21","entry":"AttentionPool2d","repo":"x-cls/superclass","repo_kind":"official","path":"opencls/open_clip/cls_model.py","file_url":"https://github.com/x-cls/superclass/blob/HEAD/opencls/open_clip/cls_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"785f7419f700fb21"}},{"code_sha256_prefix":"6795bcd62138695d","entry":"AttentionalPooler","repo":"x-cls/superclass","repo_kind":"official","path":"opencls/open_clip/cls_model.py","file_url":"https://github.com/x-cls/superclass/blob/HEAD/opencls/open_clip/cls_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6795bcd62138695d"}},{"code_sha256_prefix":"4a1aa6db92310642","entry":"MixClsHead","repo":"x-cls/superclass","repo_kind":"official","path":"opencls/open_clip/cls_model.py","file_url":"https://github.com/x-cls/superclass/blob/HEAD/opencls/open_clip/cls_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4a1aa6db92310642"}},{"code_sha256_prefix":"7000ad070b2b4c5c","entry":"ResidualAttentionBlock","repo":"x-cls/superclass","repo_kind":"official","path":"opencls/open_clip/cls_model.py","file_url":"https://github.com/x-cls/superclass/blob/HEAD/opencls/open_clip/cls_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7000ad070b2b4c5c"}},{"code_sha256_prefix":"47769d892eb10b08","entry":"Transformer","repo":"x-cls/superclass","repo_kind":"official","path":"opencls/open_clip/cls_model.py","file_url":"https://github.com/x-cls/superclass/blob/HEAD/opencls/open_clip/cls_model.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":"47769d892eb10b08"}},{"code_sha256_prefix":"ef5de3709b9ce92f","entry":"_build_cls_head","repo":"x-cls/superclass","repo_kind":"official","path":"opencls/open_clip/cls_model.py","file_url":"https://github.com/x-cls/superclass/blob/HEAD/opencls/open_clip/cls_model.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":"ef5de3709b9ce92f"}},{"code_sha256_prefix":"476766d1bc74cdeb","entry":"_expand_token","repo":"x-cls/superclass","repo_kind":"official","path":"opencls/open_clip/cls_model.py","file_url":"https://github.com/x-cls/superclass/blob/HEAD/opencls/open_clip/cls_model.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":"476766d1bc74cdeb"}},{"code_sha256_prefix":"63d746eddf749201","entry":"convert_to_custom_text_state_dict","repo":"x-cls/superclass","repo_kind":"official","path":"opencls/open_clip/model.py","file_url":"https://github.com/x-cls/superclass/blob/HEAD/opencls/open_clip/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"63d746eddf749201"}},{"code_sha256_prefix":"1f22cc0143fbf7d1","entry":"get_cast_dtype","repo":"x-cls/superclass","repo_kind":"official","path":"opencls/open_clip/model.py","file_url":"https://github.com/x-cls/superclass/blob/HEAD/opencls/open_clip/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1f22cc0143fbf7d1"}},{"code_sha256_prefix":"005ae1827a1eb3f0","entry":"get_input_dtype","repo":"x-cls/superclass","repo_kind":"official","path":"opencls/open_clip/model.py","file_url":"https://github.com/x-cls/superclass/blob/HEAD/opencls/open_clip/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"005ae1827a1eb3f0"}},{"code_sha256_prefix":"8037b3f2668053ef","entry":"CLIPTextCfg","repo":"x-cls/superclass","repo_kind":"official","path":"opencls/open_clip/cls_model.py","file_url":"https://github.com/x-cls/superclass/blob/HEAD/opencls/open_clip/cls_model.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":"8037b3f2668053ef"}},{"code_sha256_prefix":"f9612255629b2c84","entry":"CLIPVisionCfg","repo":"x-cls/superclass","repo_kind":"official","path":"opencls/open_clip/cls_model.py","file_url":"https://github.com/x-cls/superclass/blob/HEAD/opencls/open_clip/cls_model.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":"f9612255629b2c84"}},{"code_sha256_prefix":"91bb6a8d9bbe9931","entry":"ClassHeadCfg","repo":"x-cls/superclass","repo_kind":"official","path":"opencls/open_clip/cls_model.py","file_url":"https://github.com/x-cls/superclass/blob/HEAD/opencls/open_clip/cls_model.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":"91bb6a8d9bbe9931"}},{"code_sha256_prefix":"b4684d62e958c830","entry":"Classifier","repo":"x-cls/superclass","repo_kind":"official","path":"opencls/open_clip/cls_model.py","file_url":"https://github.com/x-cls/superclass/blob/HEAD/opencls/open_clip/cls_model.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":"b4684d62e958c830"}},{"code_sha256_prefix":"368e98cc03933cb5","entry":"ModifiedResNet","repo":"x-cls/superclass","repo_kind":"official","path":"opencls/open_clip/cls_model.py","file_url":"https://github.com/x-cls/superclass/blob/HEAD/opencls/open_clip/cls_model.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":"368e98cc03933cb5"}},{"code_sha256_prefix":"b4828d6fa7fb63f1","entry":"TimmModel","repo":"x-cls/superclass","repo_kind":"official","path":"opencls/open_clip/cls_model.py","file_url":"https://github.com/x-cls/superclass/blob/HEAD/opencls/open_clip/cls_model.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":"b4828d6fa7fb63f1"}},{"code_sha256_prefix":"554c03cc48b8d760","entry":"VisionTransformer","repo":"x-cls/superclass","repo_kind":"official","path":"opencls/open_clip/cls_model.py","file_url":"https://github.com/x-cls/superclass/blob/HEAD/opencls/open_clip/cls_model.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":"554c03cc48b8d760"}},{"code_sha256_prefix":"4e3056128eed4cca","entry":"_build_vision_tower","repo":"x-cls/superclass","repo_kind":"official","path":"opencls/open_clip/cls_model.py","file_url":"https://github.com/x-cls/superclass/blob/HEAD/opencls/open_clip/cls_model.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":"4e3056128eed4cca"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}