{"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/connect-collapse-corrupt-learning-cross-modal","title":"Connect, Collapse, Corrupt: Learning Cross-Modal Tasks with Uni-Modal Data","arxiv_id":"2401.08567","date":"2024-01-16","proceeding":null,"authors":["Yuhui Zhang","Elaine Sui","Serena Yeung-Levy"],"abstract":"Building cross-modal applications is challenging due to limited paired multi-modal data. Recent works have shown that leveraging a pre-trained multi-modal contrastive representation space enables cross-modal tasks to be learned from uni-modal data. This is based on the assumption that contrastive optimization makes embeddings from different modalities interchangeable. However, this assumption is under-explored due to the poorly understood geometry of the multi-modal contrastive space, where a modality gap exists. In our study, we provide a theoretical explanation of this space's geometry and introduce a three-step method, $C^3$ (Connect, Collapse, Corrupt), to bridge the modality gap, enhancing the interchangeability of embeddings. Our $C^3$ method significantly improves cross-modal learning from uni-modal data, achieving state-of-the-art results on zero-shot image / audio / video captioning and text-to-image generation.","url_abs":"https://arxiv.org/abs/2401.08567v1","url_pdf":"https://arxiv.org/pdf/2401.08567v1.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":"connect-collapse-corrupt-learning-cross-modal","repo_url":"https://github.com/yuhui-zh15/c3","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"text-to-image-generation-1","task_name":"Text to Image Generation"},{"task_slug":"text-to-image-generation","task_name":"Text-to-Image Generation"},{"task_slug":"video-captioning","task_name":"Video Captioning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2401.08567","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.08567"}},"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/yuhui-zh15/c3","reach":null}],"summary":{"ran":5},"by_repo_kind":{"official":{"samples":5,"ran":5,"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":5,"samples":[{"code_sha256_prefix":"da51afe1b803f420","entry":"MlpTransformer","repo":"yuhui-zh15/c3","repo_kind":"official","path":"image_captioning/src/models/transformer_mapper.py","file_url":"https://github.com/yuhui-zh15/c3/blob/HEAD/image_captioning/src/models/transformer_mapper.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"da51afe1b803f420"}},{"code_sha256_prefix":"d65ab89c7116c485","entry":"MultiHeadAttention","repo":"yuhui-zh15/c3","repo_kind":"official","path":"image_captioning/src/models/transformer_mapper.py","file_url":"https://github.com/yuhui-zh15/c3/blob/HEAD/image_captioning/src/models/transformer_mapper.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d65ab89c7116c485"}},{"code_sha256_prefix":"b16b9ec624041908","entry":"Transformer","repo":"yuhui-zh15/c3","repo_kind":"official","path":"image_captioning/src/models/transformer_mapper.py","file_url":"https://github.com/yuhui-zh15/c3/blob/HEAD/image_captioning/src/models/transformer_mapper.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b16b9ec624041908"}},{"code_sha256_prefix":"35a267d7f92c479e","entry":"TransformerLayer","repo":"yuhui-zh15/c3","repo_kind":"official","path":"image_captioning/src/models/transformer_mapper.py","file_url":"https://github.com/yuhui-zh15/c3/blob/HEAD/image_captioning/src/models/transformer_mapper.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"35a267d7f92c479e"}},{"code_sha256_prefix":"c282dba117f9a205","entry":"TransformerMapper","repo":"yuhui-zh15/c3","repo_kind":"official","path":"image_captioning/src/models/transformer_mapper.py","file_url":"https://github.com/yuhui-zh15/c3/blob/HEAD/image_captioning/src/models/transformer_mapper.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c282dba117f9a205"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}