{"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/data-roaming-and-early-fusion-for-composed","title":"Data Roaming and Quality Assessment for Composed Image Retrieval","arxiv_id":"2303.09429","date":"2023-03-16","proceeding":null,"authors":["Matan Levy","Rami Ben-Ari","Nir Darshan","Dani Lischinski"],"abstract":"The task of Composed Image Retrieval (CoIR) involves queries that combine image and text modalities, allowing users to express their intent more effectively. However, current CoIR datasets are orders of magnitude smaller compared to other vision and language (V&L) datasets. Additionally, some of these datasets have noticeable issues, such as queries containing redundant modalities. To address these shortcomings, we introduce the Large Scale Composed Image Retrieval (LaSCo) dataset, a new CoIR dataset which is ten times larger than existing ones. Pre-training on our LaSCo, shows a noteworthy improvement in performance, even in zero-shot. Furthermore, we propose a new approach for analyzing CoIR datasets and methods, which detects modality redundancy or necessity, in queries. We also introduce a new CoIR baseline, the Cross-Attention driven Shift Encoder (CASE). This baseline allows for early fusion of modalities using a cross-attention module and employs an additional auxiliary task during training. Our experiments demonstrate that this new baseline outperforms the current state-of-the-art methods on established benchmarks like FashionIQ and CIRR.","url_abs":"https://arxiv.org/abs/2303.09429v2","url_pdf":"https://arxiv.org/pdf/2303.09429v2.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":"data-roaming-and-early-fusion-for-composed","repo_url":"https://github.com/levymsn/LaSCo","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"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"}],"methods":[{"method_slug":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[{"slug":"lasco","name":"LaSCo","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-retrieval-on-cirr","task":"Image Retrieval","dataset":"CIRR","model":"CASE (Pre-trained on LaSCo.Ca)","rank_in_archive_order":7,"of":17,"metrics":{"(Recall@5+Recall_subset@1)/2":"78.25","Recall@10":"88.75"},"uses_additional_data":true},{"leaderboard":"/sota/image-retrieval-on-cirr","task":"Image Retrieval","dataset":"CIRR","model":"CASE","rank_in_archive_order":8,"of":17,"metrics":{"(Recall@5+Recall_subset@1)/2":"77.5","Recall@10":"87.25"},"uses_additional_data":false},{"leaderboard":"/sota/image-retrieval-on-fashion-iq","task":"Image Retrieval","dataset":"Fashion IQ","model":"CASE","rank_in_archive_order":7,"of":22,"metrics":{"(Recall@10+Recall@50)/2":"59.73","Recall@10":"48.79"},"uses_additional_data":false},{"leaderboard":"/sota/image-retrieval-on-lasco","task":"Image Retrieval","dataset":"LaSCo","model":"CASE","rank_in_archive_order":1,"of":3,"metrics":{"Recall@1 (%)":"7.08"},"uses_additional_data":false},{"leaderboard":"/sota/image-retrieval-on-lasco","task":"Image Retrieval","dataset":"LaSCo","model":"BLIP4CIR","rank_in_archive_order":2,"of":3,"metrics":{"Recall@1 (%)":"4.26"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2303.09429","atlas_url":"https://app.syntology.ai/?focus=2303.09429","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":"2303.09429"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2303.09429\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2303.09429"},"call":"get_concepts_for_paper(arxiv_id=\"2303.09429\")"}],"by_repo":[{"repo":"levymsn/LaSCo","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":"d5f1c0487d7f608e030e298cb6c35870f2b519efeb62a4454e92469ab860dbab","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}