{"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/idea-increasing-text-diversity-via-online","title":"IDEA: Increasing Text Diversity via Online Multi-Label Recognition for Vision-Language Pre-training","arxiv_id":"2207.05333","date":"2022-07-12","proceeding":null,"authors":["Xinyu Huang","Youcai Zhang","Ying Cheng","Weiwei Tian","RuiWei Zhao","Rui Feng","Yuejie Zhang","Yaqian Li","Yandong Guo","Xiaobo Zhang"],"abstract":"Vision-Language Pre-training (VLP) with large-scale image-text pairs has demonstrated superior performance in various fields. However, the image-text pairs co-occurrent on the Internet typically lack explicit alignment information, which is suboptimal for VLP. Existing methods proposed to adopt an off-the-shelf object detector to utilize additional image tag information. However, the object detector is time-consuming and can only identify the pre-defined object categories, limiting the model capacity. Inspired by the observation that the texts incorporate incomplete fine-grained image information, we introduce IDEA, which stands for increasing text diversity via online multi-label recognition for VLP. IDEA shows that multi-label learning with image tags extracted from the texts can be jointly optimized during VLP. Moreover, IDEA can identify valuable image tags online to provide more explicit textual supervision. Comprehensive experiments demonstrate that IDEA can significantly boost the performance on multiple downstream datasets with a small extra computational cost.","url_abs":"https://arxiv.org/abs/2207.05333v2","url_pdf":"https://arxiv.org/pdf/2207.05333v2.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":"idea-increasing-text-diversity-via-online","repo_url":"https://github.com/xinyu1205/idea-pytorch","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"multi-label-learning","task_name":"Multi-Label Learning"},{"task_slug":"object","task_name":"Object"},{"task_slug":"tag","task_name":"TAG"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2207.05333","atlas_url":"https://app.syntology.ai/?focus=2207.05333","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.05333"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xinyu1205/idea-pytorch","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":3,"ran_fixture":2,"ran_violates":1,"unverified":3},"by_repo_kind":{"official":{"samples":9,"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":"cf9ffa02a42184af","entry":"whitespace_tokenize","repo":"xinyu1205/idea-pytorch","repo_kind":"official","path":"models/tokenization_bert.py","file_url":"https://github.com/xinyu1205/idea-pytorch/blob/HEAD/models/tokenization_bert.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":2,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cf9ffa02a42184af"}},{"code_sha256_prefix":"78ca1debd9c4ed87","entry":"autocontrast_func","repo":"xinyu1205/idea-pytorch","repo_kind":"official","path":"dataset/randaugment.py","file_url":"https://github.com/xinyu1205/idea-pytorch/blob/HEAD/dataset/randaugment.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"78ca1debd9c4ed87"}},{"code_sha256_prefix":"4c53169f63a1fcef","entry":"equalize_func","repo":"xinyu1205/idea-pytorch","repo_kind":"official","path":"dataset/randaugment.py","file_url":"https://github.com/xinyu1205/idea-pytorch/blob/HEAD/dataset/randaugment.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4c53169f63a1fcef"}},{"code_sha256_prefix":"1dd2ab205689d45b","entry":"identity_func","repo":"xinyu1205/idea-pytorch","repo_kind":"official","path":"dataset/randaugment.py","file_url":"https://github.com/xinyu1205/idea-pytorch/blob/HEAD/dataset/randaugment.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1dd2ab205689d45b"}},{"code_sha256_prefix":"c6ec173f19f5c34d","entry":"interpolate_pos_embed","repo":"xinyu1205/idea-pytorch","repo_kind":"official","path":"models/vit.py","file_url":"https://github.com/xinyu1205/idea-pytorch/blob/HEAD/models/vit.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":"c6ec173f19f5c34d"}},{"code_sha256_prefix":"e7fbc7a74a3457c7","entry":"load_vocab","repo":"xinyu1205/idea-pytorch","repo_kind":"official","path":"models/tokenization_bert.py","file_url":"https://github.com/xinyu1205/idea-pytorch/blob/HEAD/models/tokenization_bert.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e7fbc7a74a3457c7"}},{"code_sha256_prefix":"aafcff3ad1ccef6e","entry":"accuracy","repo":"xinyu1205/idea-pytorch","repo_kind":"official","path":"evaluation.py","file_url":"https://github.com/xinyu1205/idea-pytorch/blob/HEAD/evaluation.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":"aafcff3ad1ccef6e"}},{"code_sha256_prefix":"26be70dca3249c0b","entry":"load_tf_weights_in_bert","repo":"xinyu1205/idea-pytorch","repo_kind":"official","path":"models/xbert.py","file_url":"https://github.com/xinyu1205/idea-pytorch/blob/HEAD/models/xbert.py","link_basis":"harvester_set","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":"26be70dca3249c0b"}},{"code_sha256_prefix":"8a57c3e7d1cf36c7","entry":"pre_caption","repo":"xinyu1205/idea-pytorch","repo_kind":"official","path":"dataset/utils.py","file_url":"https://github.com/xinyu1205/idea-pytorch/blob/HEAD/dataset/utils.py","link_basis":"harvester_set","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":"8a57c3e7d1cf36c7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}