{"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/sentence-level-prompts-benefit-composed-image","title":"Sentence-level Prompts Benefit Composed Image Retrieval","arxiv_id":"2310.05473","date":"2023-10-09","proceeding":null,"authors":["Yang Bai","Xinxing Xu","Yong liu","Salman Khan","Fahad Khan","WangMeng Zuo","Rick Siow Mong Goh","Chun-Mei Feng"],"abstract":"Composed image retrieval (CIR) is the task of retrieving specific images by using a query that involves both a reference image and a relative caption. Most existing CIR models adopt the late-fusion strategy to combine visual and language features. Besides, several approaches have also been suggested to generate a pseudo-word token from the reference image, which is further integrated into the relative caption for CIR. However, these pseudo-word-based prompting methods have limitations when target image encompasses complex changes on reference image, e.g., object removal and attribute modification. In this work, we demonstrate that learning an appropriate sentence-level prompt for the relative caption (SPRC) is sufficient for achieving effective composed image retrieval. Instead of relying on pseudo-word-based prompts, we propose to leverage pretrained V-L models, e.g., BLIP-2, to generate sentence-level prompts. By concatenating the learned sentence-level prompt with the relative caption, one can readily use existing text-based image retrieval models to enhance CIR performance. Furthermore, we introduce both image-text contrastive loss and text prompt alignment loss to enforce the learning of suitable sentence-level prompts. Experiments show that our proposed method performs favorably against the state-of-the-art CIR methods on the Fashion-IQ and CIRR datasets. The source code and pretrained model are publicly available at https://github.com/chunmeifeng/SPRC","url_abs":"https://arxiv.org/abs/2310.05473v1","url_pdf":"https://arxiv.org/pdf/2310.05473v1.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":"sentence-level-prompts-benefit-composed-image","repo_url":"https://github.com/chunmeifeng/sprc","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"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":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-retrieval-on-cirr","task":"Image Retrieval","dataset":"CIRR","model":"SPRC2","rank_in_archive_order":3,"of":17,"metrics":{"(Recall@5+Recall_subset@1)/2":"82.66","Recall@10":"90.39"},"uses_additional_data":false},{"leaderboard":"/sota/image-retrieval-on-cirr","task":"Image Retrieval","dataset":"CIRR","model":"SPRC","rank_in_archive_order":4,"of":17,"metrics":{"(Recall@5+Recall_subset@1)/2":"81.39","Recall@10":"89.74"},"uses_additional_data":false},{"leaderboard":"/sota/image-retrieval-on-fashion-iq","task":"Image Retrieval","dataset":"Fashion IQ","model":"SPRC","rank_in_archive_order":4,"of":22,"metrics":{"(Recall@10+Recall@50)/2":"64.85","Recall@10":"54.92"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2310.05473","atlas_url":"https://app.syntology.ai/?focus=2310.05473","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.05473"}},"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/chunmeifeng/sprc","reach":{"status":"ok"}}],"summary":{"ran_honours":1,"ran_fixture":1,"ran_draft_wrong":2,"ran":2,"ran_violates":1,"unverified":1},"by_repo_kind":{"official":{"samples":8,"ran":7,"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":8,"samples":[{"code_sha256_prefix":"b6c1f837e6faaeba","entry":"collate_fn","repo":"chunmeifeng/sprc","repo_kind":"official","path":"src/data_utils.py","file_url":"https://github.com/chunmeifeng/sprc/blob/HEAD/src/data_utils.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b6c1f837e6faaeba"}},{"code_sha256_prefix":"7d214655954e2bc6","entry":"getAttMap","repo":"chunmeifeng/sprc","repo_kind":"official","path":"src/lavis/common/gradcam.py","file_url":"https://github.com/chunmeifeng/sprc/blob/HEAD/src/lavis/common/gradcam.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7d214655954e2bc6"}},{"code_sha256_prefix":"98589643273920ba","entry":"main_process","repo":"chunmeifeng/sprc","repo_kind":"official","path":"src/lavis/common/dist_utils.py","file_url":"https://github.com/chunmeifeng/sprc/blob/HEAD/src/lavis/common/dist_utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"98589643273920ba"}},{"code_sha256_prefix":"791c72070c0b1cfb","entry":"node_to_dict","repo":"chunmeifeng/sprc","repo_kind":"official","path":"src/lavis/common/config.py","file_url":"https://github.com/chunmeifeng/sprc/blob/HEAD/src/lavis/common/config.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"791c72070c0b1cfb"}},{"code_sha256_prefix":"a1580dd1883758f6","entry":"squarepad_transform","repo":"chunmeifeng/sprc","repo_kind":"official","path":"src/data_utils.py","file_url":"https://github.com/chunmeifeng/sprc/blob/HEAD/src/data_utils.py","link_basis":"harvester_set","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":"a1580dd1883758f6"}},{"code_sha256_prefix":"7c508037b40522af","entry":"str2bool","repo":"chunmeifeng/sprc","repo_kind":"official","path":"src/cirr_test_submission.py","file_url":"https://github.com/chunmeifeng/sprc/blob/HEAD/src/cirr_test_submission.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7c508037b40522af"}},{"code_sha256_prefix":"9e2b18431cf6776f","entry":"targetpad_transform","repo":"chunmeifeng/sprc","repo_kind":"official","path":"src/data_utils.py","file_url":"https://github.com/chunmeifeng/sprc/blob/HEAD/src/data_utils.py","link_basis":"harvester_set","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":"9e2b18431cf6776f"}},{"code_sha256_prefix":"643539116e049080","entry":"download_cached_file","repo":"chunmeifeng/sprc","repo_kind":"official","path":"src/lavis/common/dist_utils.py","file_url":"https://github.com/chunmeifeng/sprc/blob/HEAD/src/lavis/common/dist_utils.py","link_basis":"harvester_set","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":"643539116e049080"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}