{"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/pretrain-like-you-inference-masked-tuning","title":"Pretrain like Your Inference: Masked Tuning Improves Zero-Shot Composed Image Retrieval","arxiv_id":"2311.07622","date":"2023-11-13","proceeding":null,"authors":["Junyang Chen","Hanjiang Lai"],"abstract":"Zero-shot composed image retrieval (ZS-CIR), which takes a textual modification and a reference image as a query to retrieve a target image without triplet labeling, has gained more and more attention in data mining. Current ZS-CIR research mainly relies on the generalization ability of pre-trained vision-language models, e.g., CLIP. However, the pre-trained vision-language models and CIR tasks have substantial discrepancies, where the vision-language models focus on learning the similarities but CIR aims to learn the modifications of the image guided by text. In this paper, we introduce a novel unlabeled and pre-trained masked tuning approach, which reduces the gap between the pre-trained vision-language model and the downstream CIR task. First, to reduce the gap, we reformulate the contrastive learning of the vision-language model as the CIR task, where we randomly mask input image patches to generate $\\langle$masked image, text, image$\\rangle$ triplet from an image-text pair. Then, we propose a simple but novel pre-trained masked tuning method, which uses the text and the masked image to learn the modifications of the original image. With such a simple design, the proposed masked tuning can learn to better capture fine-grained text-guided modifications. Extensive experimental results demonstrate the significant superiority of our approach over the baseline models on four ZS-CIR datasets, including FashionIQ, CIRR, CIRCO, and GeneCIS. Our codes are available at https://github.com/Chen-Junyang-cn/PLI","url_abs":"https://arxiv.org/abs/2311.07622v3","url_pdf":"https://arxiv.org/pdf/2311.07622v3.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":"pretrain-like-you-inference-masked-tuning","repo_url":"https://github.com/Chen-Junyang-cn/PLI","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"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":null,"task_name":"Triplet"},{"task_slug":"zero-shot-composed-image-retrieval-zs-cir","task_name":"Zero-Shot Composed Image Retrieval (ZS-CIR)"}],"methods":[{"method_slug":"clip","method_name":"CLIP"},{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/zero-shot-composed-image-retrieval-zs-cir-on","task":"Zero-Shot Composed Image Retrieval (ZS-CIR)","dataset":"CIRCO","model":"MTCIR (CLIP L/14)","rank_in_archive_order":37,"of":43,"metrics":{"mAP@10":"11.63"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-composed-image-retrieval-zs-cir-on","task":"Zero-Shot Composed Image Retrieval (ZS-CIR)","dataset":"CIRCO","model":"MTCIR (BLIP B/16)","rank_in_archive_order":42,"of":43,"metrics":{"mAP@10":"8.03"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-composed-image-retrieval-zs-cir-on-1","task":"Zero-Shot Composed Image Retrieval (ZS-CIR)","dataset":"CIRR","model":"MTCIR (BLIP B/16)","rank_in_archive_order":28,"of":47,"metrics":{"R@5":"58.87"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-composed-image-retrieval-zs-cir-on-1","task":"Zero-Shot Composed Image Retrieval (ZS-CIR)","dataset":"CIRR","model":"MTCIR (CLIP L/14)","rank_in_archive_order":39,"of":47,"metrics":{"R@5":"54.58"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-composed-image-retrieval-zs-cir-on-2","task":"Zero-Shot Composed Image Retrieval (ZS-CIR)","dataset":"Fashion IQ","model":"MTCIR (CLIP L/14)","rank_in_archive_order":10,"of":41,"metrics":{"(Recall@10+Recall@50)/2":"46.42"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2311.07622","atlas_url":"https://app.syntology.ai/?focus=2311.07622","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.07622"}},"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/Chen-Junyang-cn/PLI","reach":null}],"summary":{"ran_honours":1,"ran_fixture":1,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":4,"ran":3,"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":4,"samples":[{"code_sha256_prefix":"b6c1f837e6faaeba","entry":"collate_fn","repo":"Chen-Junyang-cn/PLI","repo_kind":"official","path":"circo_test_submission.py","file_url":"https://github.com/Chen-Junyang-cn/PLI/blob/HEAD/circo_test_submission.py","link_basis":"first_harvest_node","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":"120655737600ab08","entry":"get_recall","repo":"Chen-Junyang-cn/PLI","repo_kind":"official","path":"genecis_eval.py","file_url":"https://github.com/Chen-Junyang-cn/PLI/blob/HEAD/genecis_eval.py","link_basis":"first_harvest_node","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":"120655737600ab08"}},{"code_sha256_prefix":"6977e9b491f237fb","entry":"load_model","repo":"Chen-Junyang-cn/PLI","repo_kind":"official","path":"genecis_eval.py","file_url":"https://github.com/Chen-Junyang-cn/PLI/blob/HEAD/genecis_eval.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6977e9b491f237fb"}},{"code_sha256_prefix":"78085af70623ee31","entry":"validate","repo":"Chen-Junyang-cn/PLI","repo_kind":"official","path":"genecis_eval.py","file_url":"https://github.com/Chen-Junyang-cn/PLI/blob/HEAD/genecis_eval.py","link_basis":"first_harvest_node","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":"78085af70623ee31"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}