{"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/rankclip-ranking-consistent-language-image","title":"RankCLIP: Ranking-Consistent Language-Image Pretraining","arxiv_id":"2404.09387","date":"2024-04-15","proceeding":null,"authors":["Yiming Zhang","Zhuokai Zhao","Zhaorun Chen","Zhili Feng","Zenghui Ding","Yining Sun"],"abstract":"Self-supervised contrastive learning models, such as CLIP, have set new benchmarks for vision-language models in many downstream tasks. However, their dependency on rigid one-to-one mappings overlooks the complex and often multifaceted relationships between and within texts and images. To this end, we introduce RANKCLIP, a novel pretraining method that extends beyond the rigid one-to-one matching framework of CLIP and its variants. By extending the traditional pair-wise loss to list-wise, and leveraging both in-modal and cross-modal ranking consistency, RANKCLIP improves the alignment process, enabling it to capture the nuanced many-to-many relationships between and within each modality. Through comprehensive experiments, we demonstrate the effectiveness of RANKCLIP in various downstream tasks, notably achieving significant gains in zero-shot classifications over state-of-the-art methods, underscoring the importance of this enhanced learning process.","url_abs":"https://arxiv.org/abs/2404.09387v2","url_pdf":"https://arxiv.org/pdf/2404.09387v2.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":"rankclip-ranking-consistent-language-image","repo_url":"https://github.com/jam1ezhang/rankclip","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"}],"methods":[{"method_slug":"clip","method_name":"CLIP"},{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"},{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2404.09387","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.09387"}},"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/jam1ezhang/rankclip","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":3,"ran":5,"unverified":3},"by_repo_kind":{"official":{"samples":11,"ran":8,"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":11,"samples":[{"code_sha256_prefix":"98f385d847636a3e","entry":"basic_clean","repo":"jam1ezhang/rankclip","repo_kind":"official","path":"pkgs/openai/tokenizer.py","file_url":"https://github.com/jam1ezhang/rankclip/blob/HEAD/pkgs/openai/tokenizer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"98f385d847636a3e"}},{"code_sha256_prefix":"46183da5ef12e371","entry":"cosine_scheduler","repo":"jam1ezhang/rankclip","repo_kind":"official","path":"rankclip/scheduler.py","file_url":"https://github.com/jam1ezhang/rankclip/blob/HEAD/rankclip/scheduler.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"46183da5ef12e371"}},{"code_sha256_prefix":"7a0637e7b331c50b","entry":"get_eval_test_dataloader","repo":"jam1ezhang/rankclip","repo_kind":"official","path":"rankclip/data.py","file_url":"https://github.com/jam1ezhang/rankclip/blob/HEAD/rankclip/data.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7a0637e7b331c50b"}},{"code_sha256_prefix":"75f67d27c89765cd","entry":"get_logger","repo":"jam1ezhang/rankclip","repo_kind":"official","path":"rankclip/logger.py","file_url":"https://github.com/jam1ezhang/rankclip/blob/HEAD/rankclip/logger.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"75f67d27c89765cd"}},{"code_sha256_prefix":"d919ae32e5e4e616","entry":"get_pairs","repo":"jam1ezhang/rankclip","repo_kind":"official","path":"pkgs/openai/tokenizer.py","file_url":"https://github.com/jam1ezhang/rankclip/blob/HEAD/pkgs/openai/tokenizer.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d919ae32e5e4e616"}},{"code_sha256_prefix":"0b28dcd05f77beac","entry":"get_validation_metrics","repo":"jam1ezhang/rankclip","repo_kind":"official","path":"rankclip/evaluate.py","file_url":"https://github.com/jam1ezhang/rankclip/blob/HEAD/rankclip/evaluate.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0b28dcd05f77beac"}},{"code_sha256_prefix":"510990172d8d5591","entry":"list_MLE","repo":"jam1ezhang/rankclip","repo_kind":"official","path":"rankclip/rank_losses.py","file_url":"https://github.com/jam1ezhang/rankclip/blob/HEAD/rankclip/rank_losses.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"510990172d8d5591"}},{"code_sha256_prefix":"9542161e9640b858","entry":"whitespace_clean","repo":"jam1ezhang/rankclip","repo_kind":"official","path":"pkgs/openai/tokenizer.py","file_url":"https://github.com/jam1ezhang/rankclip/blob/HEAD/pkgs/openai/tokenizer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9542161e9640b858"}},{"code_sha256_prefix":"27b459903dd9ce81","entry":"build","repo":"jam1ezhang/rankclip","repo_kind":"official","path":"pkgs/openai/model.py","file_url":"https://github.com/jam1ezhang/rankclip/blob/HEAD/pkgs/openai/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"27b459903dd9ce81"}},{"code_sha256_prefix":"839f27352544a030","entry":"get_linear_probe_metrics","repo":"jam1ezhang/rankclip","repo_kind":"official","path":"rankclip/evaluate.py","file_url":"https://github.com/jam1ezhang/rankclip/blob/HEAD/rankclip/evaluate.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"839f27352544a030"}},{"code_sha256_prefix":"8718f0ef4c825c28","entry":"get_zeroshot_metrics","repo":"jam1ezhang/rankclip","repo_kind":"official","path":"rankclip/evaluate.py","file_url":"https://github.com/jam1ezhang/rankclip/blob/HEAD/rankclip/evaluate.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8718f0ef4c825c28"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}