{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/bi-directional-training-for-composed-image","title":"Bi-directional Training for Composed Image Retrieval via Text Prompt Learning","arxiv_id":"2303.16604","date":"2023-03-29","proceeding":null,"authors":["Zheyuan Liu","Weixuan Sun","Yicong Hong","Damien Teney","Stephen Gould"],"abstract":"Composed image retrieval searches for a target image based on a multi-modal user query comprised of a reference image and modification text describing the desired changes. Existing approaches to solving this challenging task learn a mapping from the (reference image, modification text)-pair to an image embedding that is then matched against a large image corpus. One area that has not yet been explored is the reverse direction, which asks the question, what reference image when modified as described by the text would produce the given target image? In this work we propose a bi-directional training scheme that leverages such reversed queries and can be applied to existing composed image retrieval architectures with minimum changes, which improves the performance of the model. To encode the bi-directional query we prepend a learnable token to the modification text that designates the direction of the query and then finetune the parameters of the text embedding module. We make no other changes to the network architecture. Experiments on two standard datasets show that our novel approach achieves improved performance over a baseline BLIP-based model that itself already achieves competitive performance. Our code is released at https://github.com/Cuberick-Orion/Bi-Blip4CIR.","url_abs":"https://arxiv.org/abs/2303.16604v2","url_pdf":"https://arxiv.org/pdf/2303.16604v2.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":"bi-directional-training-for-composed-image","repo_url":"https://github.com/Cuberick-Orion/Bi-Blip4CIR","is_official":1,"mentioned_in_paper":1,"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":"prompt-learning","task_name":"Prompt Learning"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-retrieval-on-cirr","task":"Image Retrieval","dataset":"CIRR","model":"BLIP4CIR+Bi","rank_in_archive_order":13,"of":17,"metrics":{"(Recall@5+Recall_subset@1)/2":"72.59","Recall@10":"83.88"},"uses_additional_data":false},{"leaderboard":"/sota/image-retrieval-on-fashion-iq","task":"Image Retrieval","dataset":"Fashion IQ","model":"BLIP4CIR+Bi","rank_in_archive_order":9,"of":22,"metrics":{"(Recall@10+Recall@50)/2":"55.4"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2303.16604","atlas_url":"https://app.syntology.ai/?focus=2303.16604","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2303.16604"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2303.16604\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2303.16604"},"call":"get_concepts_for_paper(arxiv_id=\"2303.16604\")"}],"by_repo":[{"repo":"Cuberick-Orion/Bi-Blip4CIR","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2305.16304"],"harvested_for_calls":[{"arxiv_id":"2305.16304","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2305.16304"},"call":"get_harvested_code_for_paper(arxiv_id=\"2305.16304\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"0a3e97324f780ddd5cbcf3742ee7ed7f693d4fe3441439479fc7be726368adc7","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}