{"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/training-and-challenging-models-for-text","title":"Training and challenging models for text-guided fashion image retrieval","arxiv_id":"2204.11004","date":"2022-04-23","proceeding":null,"authors":["Eric Dodds","Jack Culpepper","Gaurav Srivastava"],"abstract":"Retrieving relevant images from a catalog based on a query image together with a modifying caption is a challenging multimodal task that can particularly benefit domains like apparel shopping, where fine details and subtle variations may be best expressed through natural language. We introduce a new evaluation dataset, Challenging Fashion Queries (CFQ), as well as a modeling approach that achieves state-of-the-art performance on the existing Fashion IQ (FIQ) dataset. CFQ complements existing benchmarks by including relative captions with positive and negative labels of caption accuracy and conditional image similarity, where others provided only positive labels with a combined meaning. We demonstrate the importance of multimodal pretraining for the task and show that domain-specific weak supervision based on attribute labels can augment generic large-scale pretraining. While previous modality fusion mechanisms lose the benefits of multimodal pretraining, we introduce a residual attention fusion mechanism that improves performance. We release CFQ and our code to the research community.","url_abs":"https://arxiv.org/abs/2204.11004v1","url_pdf":"https://arxiv.org/pdf/2204.11004v1.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":"training-and-challenging-models-for-text","repo_url":"https://github.com/yahoo/maaf","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":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2204.11004","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.11004"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/yahoo/maaf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":7},"by_repo_kind":{"official":{"samples":7,"ran":0,"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":7,"samples":[{"code_sha256_prefix":"9344f92216a6288e","entry":"compute_db_features","repo":"yahoo/maaf","repo_kind":"official","path":"src/maaf/actions/eval_retrieval.py","file_url":"https://github.com/yahoo/maaf/blob/HEAD/src/maaf/actions/eval_retrieval.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"9344f92216a6288e"}},{"code_sha256_prefix":"7a2e100337d6f2e1","entry":"config_from_args","repo":"yahoo/maaf","repo_kind":"official","path":"src/maaf/config/compat.py","file_url":"https://github.com/yahoo/maaf/blob/HEAD/src/maaf/config/compat.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"7a2e100337d6f2e1"}},{"code_sha256_prefix":"6a068ae681867832","entry":"get_augmenting_image_transform","repo":"yahoo/maaf","repo_kind":"official","path":"src/maaf/datasets/datasets.py","file_url":"https://github.com/yahoo/maaf/blob/HEAD/src/maaf/datasets/datasets.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"6a068ae681867832"}},{"code_sha256_prefix":"5e21d0469bc295c9","entry":"get_default_image_transform","repo":"yahoo/maaf","repo_kind":"official","path":"src/maaf/datasets/datasets.py","file_url":"https://github.com/yahoo/maaf/blob/HEAD/src/maaf/datasets/datasets.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"5e21d0469bc295c9"}},{"code_sha256_prefix":"584d378d1f7c1f34","entry":"load_dataset","repo":"yahoo/maaf","repo_kind":"official","path":"src/maaf/datasets/datasets.py","file_url":"https://github.com/yahoo/maaf/blob/HEAD/src/maaf/datasets/datasets.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"584d378d1f7c1f34"}},{"code_sha256_prefix":"27085937241d0abc","entry":"nn_and_sims","repo":"yahoo/maaf","repo_kind":"official","path":"src/maaf/actions/eval_retrieval.py","file_url":"https://github.com/yahoo/maaf/blob/HEAD/src/maaf/actions/eval_retrieval.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"27085937241d0abc"}},{"code_sha256_prefix":"782c00ebf1cbbc1c","entry":"test","repo":"yahoo/maaf","repo_kind":"official","path":"src/maaf/actions/eval_retrieval.py","file_url":"https://github.com/yahoo/maaf/blob/HEAD/src/maaf/actions/eval_retrieval.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"782c00ebf1cbbc1c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}