{"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/prompting-language-informed-distribution-for","title":"Prompting Language-Informed Distribution for Compositional Zero-Shot Learning","arxiv_id":"2305.14428","date":"2023-05-23","proceeding":null,"authors":["Wentao Bao","Lichang Chen","Heng Huang","Yu Kong"],"abstract":"Compositional zero-shot learning (CZSL) task aims to recognize unseen compositional visual concepts, e.g., sliced tomatoes, where the model is learned only from the seen compositions, e.g., sliced potatoes and red tomatoes. Thanks to the prompt tuning on large pre-trained visual language models such as CLIP, recent literature shows impressively better CZSL performance than traditional vision-based methods. However, the key aspects that impact the generalization to unseen compositions, including the diversity and informativeness of class context, and the entanglement between visual primitives, i.e., state and object, are not properly addressed in existing CLIP-based CZSL literature. In this paper, we propose a model by prompting the language-informed distribution, aka., PLID, for the CZSL task. Specifically, the PLID leverages pre-trained large language models (LLM) to (i) formulate the language-informed class distributions which are diverse and informative, and (ii) enhance the compositionality of the class embedding. Moreover, a visual-language primitive decomposition (VLPD) module is proposed to dynamically fuse the classification decisions from the compositional and the primitive space. Orthogonal to the existing literature of soft, hard, or distributional prompts, our method advocates prompting the LLM-supported class distributions, leading to a better zero-shot generalization. Experimental results on MIT-States, UT-Zappos, and C-GQA datasets show the superior performance of the PLID to the prior arts. Our code and models are released: https://github.com/Cogito2012/PLID.","url_abs":"https://arxiv.org/abs/2305.14428v3","url_pdf":"https://arxiv.org/pdf/2305.14428v3.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":"prompting-language-informed-distribution-for","repo_url":"https://github.com/cogito2012/plid","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"tasks":[{"task_slug":"compositional-zero-shot-learning","task_name":"Compositional Zero-Shot Learning"},{"task_slug":"informativeness","task_name":"Informativeness"},{"task_slug":"zero-shot-learning","task_name":"Zero-Shot Learning"},{"task_slug":"zero-shot-generalization","task_name":"Zero-shot Generalization"}],"methods":[{"method_slug":"clip","method_name":"CLIP"},{"method_slug":"mixup","method_name":"Mixup"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.14428","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14428"}},"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/cogito2012/plid","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"summary":{"ran_draft_wrong":3,"unverified":5},"by_repo_kind":{"official":{"samples":8,"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":0,"samples":[{"code_sha256_prefix":"160bb5f66cd8558e","entry":"kernelMatrixGaussian","repo":"cogito2012/plid","repo_kind":"official","path":"models/hsic.py","file_url":"https://github.com/cogito2012/plid/blob/HEAD/models/hsic.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"160bb5f66cd8558e"}},{"code_sha256_prefix":"9ff5c4ac3b4e9b35","entry":"kernelMatrixLinear","repo":"cogito2012/plid","repo_kind":"official","path":"models/hsic.py","file_url":"https://github.com/cogito2012/plid/blob/HEAD/models/hsic.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"9ff5c4ac3b4e9b35"}},{"code_sha256_prefix":"21bf8deeec959d90","entry":"pairwise_distances","repo":"cogito2012/plid","repo_kind":"official","path":"models/hsic.py","file_url":"https://github.com/cogito2012/plid/blob/HEAD/models/hsic.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"21bf8deeec959d90"}},{"code_sha256_prefix":"4f8ed975b63f1ee7","entry":"decompose_texts","repo":"cogito2012/plid","repo_kind":"official","path":"models/losses.py","file_url":"https://github.com/cogito2012/plid/blob/HEAD/models/losses.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"4f8ed975b63f1ee7"}},{"code_sha256_prefix":"c888066e5cdf0438","entry":"get_text_representations","repo":"cogito2012/plid","repo_kind":"official","path":"evaluate.py","file_url":"https://github.com/cogito2012/plid/blob/HEAD/evaluate.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"c888066e5cdf0438"}},{"code_sha256_prefix":"284a5e2bf37a9aff","entry":"load_feasibilities","repo":"cogito2012/plid","repo_kind":"official","path":"evaluate.py","file_url":"https://github.com/cogito2012/plid/blob/HEAD/evaluate.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"284a5e2bf37a9aff"}},{"code_sha256_prefix":"b9ea6f47549f58c9","entry":"upperbound_group_logits","repo":"cogito2012/plid","repo_kind":"official","path":"models/losses.py","file_url":"https://github.com/cogito2012/plid/blob/HEAD/models/losses.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"b9ea6f47549f58c9"}},{"code_sha256_prefix":"56ed2be1f48ae4e6","entry":"upperbound_logits","repo":"cogito2012/plid","repo_kind":"official","path":"models/losses.py","file_url":"https://github.com/cogito2012/plid/blob/HEAD/models/losses.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"56ed2be1f48ae4e6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}