{"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/what-does-a-platypus-look-like-generating","title":"What does a platypus look like? Generating customized prompts for zero-shot image classification","arxiv_id":"2209.03320","date":"2022-09-07","proceeding":"ICCV 2023 1","authors":["Sarah Pratt","Ian Covert","Rosanne Liu","Ali Farhadi"],"abstract":"Open-vocabulary models are a promising new paradigm for image classification. Unlike traditional classification models, open-vocabulary models classify among any arbitrary set of categories specified with natural language during inference. This natural language, called \"prompts\", typically consists of a set of hand-written templates (e.g., \"a photo of a {}\") which are completed with each of the category names. This work introduces a simple method to generate higher accuracy prompts, without relying on any explicit knowledge of the task domain and with far fewer hand-constructed sentences. To achieve this, we combine open-vocabulary models with large language models (LLMs) to create Customized Prompts via Language models (CuPL, pronounced \"couple\"). In particular, we leverage the knowledge contained in LLMs in order to generate many descriptive sentences that contain important discriminating characteristics of the image categories. This allows the model to place a greater importance on these regions in the image when making predictions. We find that this straightforward and general approach improves accuracy on a range of zero-shot image classification benchmarks, including over one percentage point gain on ImageNet. Finally, this simple baseline requires no additional training and remains completely zero-shot. Code available at https://github.com/sarahpratt/CuPL.","url_abs":"https://arxiv.org/abs/2209.03320v3","url_pdf":"https://arxiv.org/pdf/2209.03320v3.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":"what-does-a-platypus-look-like-generating","repo_url":"https://github.com/sarahpratt/cupl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"what-does-a-platypus-look-like-generating","repo_url":"https://github.com/eify/clip_benchmark","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"what-does-a-platypus-look-like-generating","repo_url":"https://github.com/laion-ai/clip_benchmark","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"descriptive","task_name":"Descriptive"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"zero-shot-image-classification","task_name":"Zero-Shot Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2209.03320","atlas_url":"https://app.syntology.ai/?focus=2209.03320","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2209.03320"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2209.03320\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2209.03320"},"call":"get_concepts_for_paper(arxiv_id=\"2209.03320\")"}],"by_repo":[{"repo":"sarahpratt/cupl","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"eify/clip_benchmark","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2309.01859"],"harvested_for_calls":[{"arxiv_id":"2309.01859","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2309.01859"},"call":"get_harvested_code_for_paper(arxiv_id=\"2309.01859\")"}]},{"repo":"laion-ai/clip_benchmark","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2507.22264"],"harvested_for_calls":[{"arxiv_id":"2507.22264","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2507.22264"},"call":"get_harvested_code_for_paper(arxiv_id=\"2507.22264\")"}]}],"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":"8ad9847694ad5bf93669a85e14947e00ce535836573aec6b6c28086f52a94dfa","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}