{"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/compodiff-versatile-composed-image-retrieval","title":"CompoDiff: Versatile Composed Image Retrieval With Latent Diffusion","arxiv_id":"2303.11916","date":"2023-03-21","proceeding":null,"authors":["Geonmo Gu","Sanghyuk Chun","Wonjae Kim","HeeJae Jun","Yoohoon Kang","Sangdoo Yun"],"abstract":"This paper proposes a novel diffusion-based model, CompoDiff, for solving zero-shot Composed Image Retrieval (ZS-CIR) with latent diffusion. This paper also introduces a new synthetic dataset, named SynthTriplets18M, with 18.8 million reference images, conditions, and corresponding target image triplets to train CIR models. CompoDiff and SynthTriplets18M tackle the shortages of the previous CIR approaches, such as poor generalizability due to the small dataset scale and the limited types of conditions. CompoDiff not only achieves a new state-of-the-art on four ZS-CIR benchmarks, including FashionIQ, CIRR, CIRCO, and GeneCIS, but also enables a more versatile and controllable CIR by accepting various conditions, such as negative text, and image mask conditions. CompoDiff also shows the controllability of the condition strength between text and image queries and the trade-off between inference speed and performance, which are unavailable with existing CIR methods. The code and dataset are available at https://github.com/navervision/CompoDiff","url_abs":"https://arxiv.org/abs/2303.11916v4","url_pdf":"https://arxiv.org/pdf/2303.11916v4.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":"compodiff-versatile-composed-image-retrieval","repo_url":"https://github.com/navervision/compodiff","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"composed-image-retrieval","task_name":"Composed Image Retrieval (CoIR)"},{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"zero-shot-composed-image-retrieval-zs-cir","task_name":"Zero-Shot Composed Image Retrieval (ZS-CIR)"}],"methods":[{"method_slug":"clip","method_name":"CLIP"},{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/zero-shot-composed-image-retrieval-zs-cir-on","task":"Zero-Shot Composed Image Retrieval (ZS-CIR)","dataset":"CIRCO","model":"CompoDiff (CLIP G/14)","rank_in_archive_order":29,"of":43,"metrics":{"mAP@10":"17.71"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-composed-image-retrieval-zs-cir-on","task":"Zero-Shot Composed Image Retrieval (ZS-CIR)","dataset":"CIRCO","model":"CompoDiff (CLIP L/14)","rank_in_archive_order":34,"of":43,"metrics":{"mAP@10":"13.51"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-composed-image-retrieval-zs-cir-on-1","task":"Zero-Shot Composed Image Retrieval (ZS-CIR)","dataset":"CIRR","model":"CompoDiff (CLIP G/14)","rank_in_archive_order":30,"of":47,"metrics":{"R@5":"57.61"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-composed-image-retrieval-zs-cir-on-1","task":"Zero-Shot Composed Image Retrieval (ZS-CIR)","dataset":"CIRR","model":"CompoDiff (CLIP L/14)","rank_in_archive_order":40,"of":47,"metrics":{"R@5":"54.36"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-composed-image-retrieval-zs-cir-on-2","task":"Zero-Shot Composed Image Retrieval (ZS-CIR)","dataset":"Fashion IQ","model":"CompoDiff (CLIP G/14)","rank_in_archive_order":11,"of":41,"metrics":{"(Recall@10+Recall@50)/2":"45.37"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-composed-image-retrieval-zs-cir-on-2","task":"Zero-Shot Composed Image Retrieval (ZS-CIR)","dataset":"Fashion IQ","model":"CompoDiff (CLIP L/14)","rank_in_archive_order":16,"of":41,"metrics":{"(Recall@10+Recall@50)/2":"44.11"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2303.11916","atlas_url":"https://app.syntology.ai/?focus=2303.11916","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.11916"}},"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/navervision/compodiff","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_honours":1,"ran_violates":2,"ran":1,"unverified":2},"by_repo_kind":{"official":{"samples":6,"ran":4,"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":"7f1040f5e3991d5e","entry":"identity","repo":"navervision/compodiff","repo_kind":"official","path":"compodiff/models.py","file_url":"https://github.com/navervision/compodiff/blob/HEAD/compodiff/models.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":2,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7f1040f5e3991d5e"}},{"code_sha256_prefix":"aa5486a3650902d8","entry":"exists","repo":"navervision/compodiff","repo_kind":"official","path":"compodiff/models.py","file_url":"https://github.com/navervision/compodiff/blob/HEAD/compodiff/models.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"aa5486a3650902d8"}},{"code_sha256_prefix":"3072294c9b32cf4b","entry":"first","repo":"navervision/compodiff","repo_kind":"official","path":"compodiff/models.py","file_url":"https://github.com/navervision/compodiff/blob/HEAD/compodiff/models.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3072294c9b32cf4b"}},{"code_sha256_prefix":"95b6310f5a3397be","entry":"l2norm","repo":"navervision/compodiff","repo_kind":"official","path":"demo_search.py","file_url":"https://github.com/navervision/compodiff/blob/HEAD/demo_search.py","link_basis":"harvester_set","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":"95b6310f5a3397be"}},{"code_sha256_prefix":"34e095c973aa68ab","entry":"build_model","repo":"navervision/compodiff","repo_kind":"official","path":"compodiff/model_loader.py","file_url":"https://github.com/navervision/compodiff/blob/HEAD/compodiff/model_loader.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":"34e095c973aa68ab"}},{"code_sha256_prefix":"63a099788570229c","entry":"predict","repo":"navervision/compodiff","repo_kind":"official","path":"demo_search.py","file_url":"https://github.com/navervision/compodiff/blob/HEAD/demo_search.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":"63a099788570229c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}