{"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/candidate-set-re-ranking-for-composed-image","title":"Candidate Set Re-ranking for Composed Image Retrieval with Dual Multi-modal Encoder","arxiv_id":"2305.16304","date":"2023-05-25","proceeding":null,"authors":["Zheyuan Liu","Weixuan Sun","Damien Teney","Stephen Gould"],"abstract":"Composed image retrieval aims to find an image that best matches a given multi-modal user query consisting of a reference image and text pair. Existing methods commonly pre-compute image embeddings over the entire corpus and compare these to a reference image embedding modified by the query text at test time. Such a pipeline is very efficient at test time since fast vector distances can be used to evaluate candidates, but modifying the reference image embedding guided only by a short textual description can be difficult, especially independent of potential candidates. An alternative approach is to allow interactions between the query and every possible candidate, i.e., reference-text-candidate triplets, and pick the best from the entire set. Though this approach is more discriminative, for large-scale datasets the computational cost is prohibitive since pre-computation of candidate embeddings is no longer possible. We propose to combine the merits of both schemes using a two-stage model. Our first stage adopts the conventional vector distancing metric and performs a fast pruning among candidates. Meanwhile, our second stage employs a dual-encoder architecture, which effectively attends to the input triplet of reference-text-candidate and re-ranks the candidates. Both stages utilize a vision-and-language pre-trained network, which has proven beneficial for various downstream tasks. Our method consistently outperforms state-of-the-art approaches on standard benchmarks for the task. Our implementation is available at https://github.com/Cuberick-Orion/Candidate-Reranking-CIR.","url_abs":"https://arxiv.org/abs/2305.16304v3","url_pdf":"https://arxiv.org/pdf/2305.16304v3.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":"candidate-set-re-ranking-for-composed-image","repo_url":"https://github.com/Cuberick-Orion/Candidate-Reranking-CIR","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"candidate-set-re-ranking-for-composed-image","repo_url":"https://github.com/Cuberick-Orion/Bi-Blip4CIR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"composed-image-retrieval","task_name":"Composed Image Retrieval (CoIR)"},{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"re-ranking","task_name":"Re-Ranking"},{"task_slug":"reranking","task_name":"Reranking"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":null,"task_name":"Triplet"}],"methods":[{"method_slug":"pruning","method_name":"Pruning"},{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-retrieval-on-cirr","task":"Image Retrieval","dataset":"CIRR","model":"Candidate Set Re-ranking","rank_in_archive_order":5,"of":17,"metrics":{"(Recall@5+Recall_subset@1)/2":"80.9","Recall@10":"89.78"},"uses_additional_data":false},{"leaderboard":"/sota/image-retrieval-on-fashion-iq","task":"Image Retrieval","dataset":"Fashion IQ","model":"Candidate Set Re-ranking","rank_in_archive_order":5,"of":22,"metrics":{"(Recall@10+Recall@50)/2":"62.15","Recall@10":"51.17"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2305.16304","atlas_url":"https://app.syntology.ai/?focus=2305.16304","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.16304"}},"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/Cuberick-Orion/Bi-Blip4CIR","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Cuberick-Orion/Candidate-Reranking-CIR","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":3,"ran_violates":1,"unverified":2},"by_repo_kind":{"official":{"samples":5,"ran":4,"repositories":1},"listed":{"samples":1,"ran":0,"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":"17a33f0b1f407e2a","entry":"generate_randomized_fiq_caption","repo":"Cuberick-Orion/Candidate-Reranking-CIR","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/Cuberick-Orion/Candidate-Reranking-CIR/blob/HEAD/src/utils.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"17a33f0b1f407e2a"}},{"code_sha256_prefix":"4d1d9c47619920ba","entry":"is_url","repo":"Cuberick-Orion/Candidate-Reranking-CIR","repo_kind":"official","path":"src/med.py","file_url":"https://github.com/Cuberick-Orion/Candidate-Reranking-CIR/blob/HEAD/src/med.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4d1d9c47619920ba"}},{"code_sha256_prefix":"a1580dd1883758f6","entry":"squarepad_transform","repo":"Cuberick-Orion/Candidate-Reranking-CIR","repo_kind":"official","path":"src/data_utils.py","file_url":"https://github.com/Cuberick-Orion/Candidate-Reranking-CIR/blob/HEAD/src/data_utils.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a1580dd1883758f6"}},{"code_sha256_prefix":"9e2b18431cf6776f","entry":"targetpad_transform","repo":"Cuberick-Orion/Candidate-Reranking-CIR","repo_kind":"official","path":"src/data_utils.py","file_url":"https://github.com/Cuberick-Orion/Candidate-Reranking-CIR/blob/HEAD/src/data_utils.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9e2b18431cf6776f"}},{"code_sha256_prefix":"d12ba8b8f88ca00d","entry":"collate_fn","repo":"Cuberick-Orion/Candidate-Reranking-CIR","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/Cuberick-Orion/Candidate-Reranking-CIR/blob/HEAD/src/utils.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":"d12ba8b8f88ca00d"}},{"code_sha256_prefix":"f837c334ddfa8af4","entry":"create_vit","repo":"Cuberick-Orion/Bi-Blip4CIR","repo_kind":"listed","path":"src/blip_modules/blip.py","file_url":"https://github.com/Cuberick-Orion/Bi-Blip4CIR/blob/HEAD/src/blip_modules/blip.py","link_basis":"first_harvest_node","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":"f837c334ddfa8af4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}