{"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/context-i2w-mapping-images-to-context","title":"Context-I2W: Mapping Images to Context-dependent Words for Accurate Zero-Shot Composed Image Retrieval","arxiv_id":"2309.16137","date":"2023-09-28","proceeding":null,"authors":["Yuanmin Tang","Jing Yu","Keke Gai","Jiamin Zhuang","Gang Xiong","Yue Hu","Qi Wu"],"abstract":"Different from Composed Image Retrieval task that requires expensive labels for training task-specific models, Zero-Shot Composed Image Retrieval (ZS-CIR) involves diverse tasks with a broad range of visual content manipulation intent that could be related to domain, scene, object, and attribute. The key challenge for ZS-CIR tasks is to learn a more accurate image representation that has adaptive attention to the reference image for various manipulation descriptions. In this paper, we propose a novel context-dependent mapping network, named Context-I2W, for adaptively converting description-relevant Image information into a pseudo-word token composed of the description for accurate ZS-CIR. Specifically, an Intent View Selector first dynamically learns a rotation rule to map the identical image to a task-specific manipulation view. Then a Visual Target Extractor further captures local information covering the main targets in ZS-CIR tasks under the guidance of multiple learnable queries. The two complementary modules work together to map an image to a context-dependent pseudo-word token without extra supervision. Our model shows strong generalization ability on four ZS-CIR tasks, including domain conversion, object composition, object manipulation, and attribute manipulation. It obtains consistent and significant performance boosts ranging from 1.88% to 3.60% over the best methods and achieves new state-of-the-art results on ZS-CIR. Our code is available at https://github.com/Pter61/context-i2w.","url_abs":"https://arxiv.org/abs/2309.16137v2","url_pdf":"https://arxiv.org/pdf/2309.16137v2.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":"context-i2w-mapping-images-to-context","repo_url":"https://github.com/pter61/context-i2w","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"object","task_name":"Object"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"zero-shot-composed-image-retrieval-zs-cir","task_name":"Zero-Shot Composed Image Retrieval (ZS-CIR)"},{"task_slug":"zero-shot-image-retrieval","task_name":"Zero-shot Image Retrieval"}],"methods":[{"method_slug":"clip","method_name":"CLIP"}],"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":"Context-I2W","rank_in_archive_order":31,"of":43,"metrics":{"mAP@10":"14.62"},"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":"Context-I2W (CLIP L/14)","rank_in_archive_order":38,"of":47,"metrics":{"R@5":"55.1"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-composed-image-retrieval-zs-cir-on-4","task":"Zero-Shot Composed Image Retrieval (ZS-CIR)","dataset":"COCO (Common Objects in Context)","model":"Context-I2W","rank_in_archive_order":5,"of":10,"metrics":{"Actions Recall@5":"28.5"},"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":"Context-I2W (CLIP L/14)","rank_in_archive_order":29,"of":41,"metrics":{"(Recall@10+Recall@50)/2":"38.35"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-composed-image-retrieval-zs-cir-on-11","task":"Zero-Shot Composed Image Retrieval (ZS-CIR)","dataset":"GeneCIS","model":"Context-I2W  (CLIP L/14)","rank_in_archive_order":7,"of":11,"metrics":{" A-R@1":"12.7"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-composed-image-retrieval-zs-cir-on-5","task":"Zero-Shot Composed Image Retrieval (ZS-CIR)","dataset":"ImageNet","model":"Context-I2W","rank_in_archive_order":6,"of":11,"metrics":{"Average Recall":"20.25"},"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":"Context-I2W","rank_in_archive_order":9,"of":20,"metrics":{"(Recall@10+Recall@50)/2":"20.25"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2309.16137","atlas_url":"https://app.syntology.ai/?focus=2309.16137","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.16137"}},"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/pter61/context-i2w","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_fixture":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"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":"4aefc9c8f821ec23","entry":"get_loss","repo":"pter61/context-i2w","repo_kind":"official","path":"src/trainer.py","file_url":"https://github.com/pter61/context-i2w/blob/HEAD/src/trainer.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4aefc9c8f821ec23"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}