{"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/composed-image-retrieval-for-training-free","title":"Composed Image Retrieval for Training-Free Domain Conversion","arxiv_id":"2412.03297","date":"2024-12-04","proceeding":null,"authors":["Nikos Efthymiadis","Bill Psomas","Zakaria Laskar","Konstantinos Karantzalos","Yannis Avrithis","Ondřej Chum","Giorgos Tolias"],"abstract":"This work addresses composed image retrieval in the context of domain conversion, where the content of a query image is retrieved in the domain specified by the query text. We show that a strong vision-language model provides sufficient descriptive power without additional training. The query image is mapped to the text input space using textual inversion. Unlike common practice that invert in the continuous space of text tokens, we use the discrete word space via a nearest-neighbor search in a text vocabulary. With this inversion, the image is softly mapped across the vocabulary and is made more robust using retrieval-based augmentation. Database images are retrieved by a weighted ensemble of text queries combining mapped words with the domain text. Our method outperforms prior art by a large margin on standard and newly introduced benchmarks. Code: https://github.com/NikosEfth/freedom","url_abs":"https://arxiv.org/abs/2412.03297v1","url_pdf":"https://arxiv.org/pdf/2412.03297v1.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":"composed-image-retrieval-for-training-free","repo_url":"https://github.com/nikosefth/freedom","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"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":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/zero-shot-composed-image-retrieval-zs-cir-on-6","task":"Zero-Shot Composed Image Retrieval (ZS-CIR)","dataset":"ImageNet-R","model":"FreeDom (CLIP-L/14)","rank_in_archive_order":15,"of":20,"metrics":{"mAP":"29.91"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-composed-image-retrieval-zs-cir-on-6","task":"Zero-Shot Composed Image Retrieval (ZS-CIR)","dataset":"ImageNet-R","model":"SEARLE (CLIP-L/14)","rank_in_archive_order":16,"of":20,"metrics":{"mAP":"14.04"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-composed-image-retrieval-zs-cir-on-6","task":"Zero-Shot Composed Image Retrieval (ZS-CIR)","dataset":"ImageNet-R","model":"CompoDiff (CLIP-L/14)","rank_in_archive_order":17,"of":20,"metrics":{"mAP":"12.88"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-composed-image-retrieval-zs-cir-on-6","task":"Zero-Shot Composed Image Retrieval (ZS-CIR)","dataset":"ImageNet-R","model":"WeiCom (CLIP-L/14)","rank_in_archive_order":18,"of":20,"metrics":{"mAP":"10.47"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-composed-image-retrieval-zs-cir-on-6","task":"Zero-Shot Composed Image Retrieval (ZS-CIR)","dataset":"ImageNet-R","model":"MagicLens (CLIP-L/14)","rank_in_archive_order":19,"of":20,"metrics":{"mAP":"9.13"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-composed-image-retrieval-zs-cir-on-6","task":"Zero-Shot Composed Image Retrieval (ZS-CIR)","dataset":"ImageNet-R","model":"Pic2Word (CLIP-L/14)","rank_in_archive_order":20,"of":20,"metrics":{"mAP":"7.88"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-composed-image-retrieval-zs-cir-on-9","task":"Zero-Shot Composed Image Retrieval (ZS-CIR)","dataset":"Large Time Lags Location (LTLL)","model":"FreeDom (CLIP-L/14)","rank_in_archive_order":1,"of":6,"metrics":{"mAP":"33.24"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-composed-image-retrieval-zs-cir-on-9","task":"Zero-Shot Composed Image Retrieval (ZS-CIR)","dataset":"Large Time Lags Location (LTLL)","model":"WeiCom (CLIP-L/14)","rank_in_archive_order":2,"of":6,"metrics":{"mAP":"26.6"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-composed-image-retrieval-zs-cir-on-9","task":"Zero-Shot Composed Image Retrieval (ZS-CIR)","dataset":"Large Time Lags Location (LTLL)","model":"SEARLE (CLIP-L/14)","rank_in_archive_order":3,"of":6,"metrics":{"mAP":"25.46"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-composed-image-retrieval-zs-cir-on-9","task":"Zero-Shot Composed Image Retrieval (ZS-CIR)","dataset":"Large Time Lags Location (LTLL)","model":"MagicLens (CLIP-L/14)","rank_in_archive_order":4,"of":6,"metrics":{"mAP":"24.21"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-composed-image-retrieval-zs-cir-on-9","task":"Zero-Shot Composed Image Retrieval (ZS-CIR)","dataset":"Large Time Lags Location (LTLL)","model":"CompoDiff (CLIP-L/14)","rank_in_archive_order":5,"of":6,"metrics":{"mAP":"21.61"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-composed-image-retrieval-zs-cir-on-9","task":"Zero-Shot Composed Image Retrieval (ZS-CIR)","dataset":"Large Time Lags Location (LTLL)","model":"Pic2Word (CLIP-L/14)","rank_in_archive_order":6,"of":6,"metrics":{"mAP":"21.27"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-composed-image-retrieval-zs-cir-on-7","task":"Zero-Shot Composed Image Retrieval (ZS-CIR)","dataset":"MiniDomainNet","model":"FreeDom (CLIP-L/14)","rank_in_archive_order":1,"of":6,"metrics":{"mAP":"37.27"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-composed-image-retrieval-zs-cir-on-7","task":"Zero-Shot Composed Image Retrieval (ZS-CIR)","dataset":"MiniDomainNet","model":"CompoDiff (CLIP-L/14)","rank_in_archive_order":2,"of":6,"metrics":{"mAP":"22.95"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-composed-image-retrieval-zs-cir-on-7","task":"Zero-Shot Composed Image Retrieval (ZS-CIR)","dataset":"MiniDomainNet","model":"SEARLE (CLIP-L/14)","rank_in_archive_order":3,"of":6,"metrics":{"mAP":"21.78"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-composed-image-retrieval-zs-cir-on-7","task":"Zero-Shot Composed Image Retrieval (ZS-CIR)","dataset":"MiniDomainNet","model":"MagicLens (CLIP-L/14)","rank_in_archive_order":4,"of":6,"metrics":{"mAP":"20.06"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-composed-image-retrieval-zs-cir-on-7","task":"Zero-Shot Composed Image Retrieval (ZS-CIR)","dataset":"MiniDomainNet","model":"Pic2Word (CLIP-L/14)","rank_in_archive_order":5,"of":6,"metrics":{"mAP":"12"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-composed-image-retrieval-zs-cir-on-7","task":"Zero-Shot Composed Image Retrieval (ZS-CIR)","dataset":"MiniDomainNet","model":"WeiCom (CLIP-L/14)","rank_in_archive_order":6,"of":6,"metrics":{"mAP":"8.52"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-composed-image-retrieval-zs-cir-on-8","task":"Zero-Shot Composed Image Retrieval (ZS-CIR)","dataset":"NICO++","model":"FreeDom (CLIP-L/14)","rank_in_archive_order":1,"of":6,"metrics":{"mAP":"26.1"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-composed-image-retrieval-zs-cir-on-8","task":"Zero-Shot Composed Image Retrieval (ZS-CIR)","dataset":"NICO++","model":"MagicLens (CLIP-L/14)","rank_in_archive_order":2,"of":6,"metrics":{"mAP":"19.66"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-composed-image-retrieval-zs-cir-on-8","task":"Zero-Shot Composed Image Retrieval (ZS-CIR)","dataset":"NICO++","model":"SEARLE (CLIP-L/14)","rank_in_archive_order":3,"of":6,"metrics":{"mAP":"15.13"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-composed-image-retrieval-zs-cir-on-8","task":"Zero-Shot Composed Image Retrieval (ZS-CIR)","dataset":"NICO++","model":"WeiCom (CLIP-L/14)","rank_in_archive_order":4,"of":6,"metrics":{"mAP":"10.54"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-composed-image-retrieval-zs-cir-on-8","task":"Zero-Shot Composed Image Retrieval (ZS-CIR)","dataset":"NICO++","model":"CompoDiff (CLIP-L/14)","rank_in_archive_order":5,"of":6,"metrics":{"mAP":"10.32"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-composed-image-retrieval-zs-cir-on-8","task":"Zero-Shot Composed Image Retrieval (ZS-CIR)","dataset":"NICO++","model":"Pic2Word (CLIP-L/14)","rank_in_archive_order":6,"of":6,"metrics":{"mAP":"9.76"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[{"repo":"nikosefth/freedom","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1711.02512"],"harvested_for_calls":[{"arxiv_id":"1711.02512","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1711.02512"},"call":"get_harvested_code_for_paper(arxiv_id=\"1711.02512\")"}]}],"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":"e261be7b66abbba0d01cda8ca3f346c519b736b7dc4503281d918c2904bc2270","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}