{"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/prompt-pre-training-with-twenty-thousand-1","title":"Prompt Pre-Training with Twenty-Thousand Classes for Open-Vocabulary Visual Recognition","arxiv_id":"2304.04704","date":"2023-04-10","proceeding":"NeurIPS 2023 11","authors":["Shuhuai Ren","Aston Zhang","Yi Zhu","Shuai Zhang","Shuai Zheng","Mu Li","Alex Smola","Xu sun"],"abstract":"This work proposes POMP, a prompt pre-training method for vision-language models. Being memory and computation efficient, POMP enables the learned prompt to condense semantic information for a rich set of visual concepts with over twenty-thousand classes. Once pre-trained, the prompt with a strong transferable ability can be directly plugged into a variety of visual recognition tasks including image classification, semantic segmentation, and object detection, to boost recognition performances in a zero-shot manner. Empirical evaluation shows that POMP achieves state-of-the-art performances on 21 datasets, e.g., 67.0% average accuracy on 10 classification datasets (+3.1% compared to CoOp) and 84.4 hIoU on open-vocabulary Pascal VOC segmentation (+6.9 compared to ZSSeg). Our code is available at https://github.com/amazon-science/prompt-pretraining.","url_abs":"https://arxiv.org/abs/2304.04704v2","url_pdf":"https://arxiv.org/pdf/2304.04704v2.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":"prompt-pre-training-with-twenty-thousand-1","repo_url":"https://github.com/amazon-science/prompt-pretraining","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"image-classification","task_name":"image-classification"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/open-vocabulary-object-detection-on-lvis-v1-0","task":"Open Vocabulary Object Detection","dataset":"LVIS v1.0","model":"POMP","rank_in_archive_order":16,"of":28,"metrics":{"AP novel-LVIS base training":"25.2"},"uses_additional_data":false},{"leaderboard":"/sota/open-vocabulary-semantic-segmentation-on-coco","task":"Open Vocabulary Semantic Segmentation","dataset":"COCO-Stuff-171","model":"POMP","rank_in_archive_order":1,"of":7,"metrics":{"HIoU":"39.1"},"uses_additional_data":false},{"leaderboard":"/sota/open-vocabulary-semantic-segmentation-on-5","task":"Open Vocabulary Semantic Segmentation","dataset":"PascalVOC-20","model":"POMP","rank_in_archive_order":13,"of":20,"metrics":{"hIoU":"84.4","mIoU":"89.4"},"uses_additional_data":false},{"leaderboard":"/sota/prompt-engineering-on-imagenet-21k","task":"Prompt Engineering","dataset":"ImageNet-21k","model":"POMP","rank_in_archive_order":1,"of":2,"metrics":{"Accuracy":"25.3"},"uses_additional_data":false},{"leaderboard":"/sota/prompt-engineering-on-imagenet-a","task":"Prompt Engineering","dataset":"ImageNet-A","model":"POMP","rank_in_archive_order":1,"of":9,"metrics":{"Top-1 accuracy %":"51.6"},"uses_additional_data":false},{"leaderboard":"/sota/prompt-engineering-on-imagenet-r","task":"Prompt Engineering","dataset":"ImageNet-R","model":"POMP","rank_in_archive_order":1,"of":9,"metrics":{"Top-1 accuracy %":"77.9"},"uses_additional_data":false},{"leaderboard":"/sota/prompt-engineering-on-imagenet-s","task":"Prompt Engineering","dataset":"ImageNet-S","model":"POMP","rank_in_archive_order":1,"of":9,"metrics":{"Top-1 accuracy %":"49.8"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2304.04704","atlas_url":"https://app.syntology.ai/?focus=2304.04704","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.04704"}},"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/amazon-science/prompt-pretraining","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":2,"ran_draft_wrong":3,"unverified":2},"by_repo_kind":{"official":{"samples":7,"ran":5,"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":"ebb1a59bc40babbb","entry":"align_loss","repo":"amazon-science/prompt-pretraining","repo_kind":"official","path":"align_uniform.py","file_url":"https://github.com/amazon-science/prompt-pretraining/blob/HEAD/align_uniform.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ebb1a59bc40babbb"}},{"code_sha256_prefix":"98f385d847636a3e","entry":"basic_clean","repo":"amazon-science/prompt-pretraining","repo_kind":"official","path":"clip/simple_tokenizer.py","file_url":"https://github.com/amazon-science/prompt-pretraining/blob/HEAD/clip/simple_tokenizer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"98f385d847636a3e"}},{"code_sha256_prefix":"d919ae32e5e4e616","entry":"get_pairs","repo":"amazon-science/prompt-pretraining","repo_kind":"official","path":"clip/simple_tokenizer.py","file_url":"https://github.com/amazon-science/prompt-pretraining/blob/HEAD/clip/simple_tokenizer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d919ae32e5e4e616"}},{"code_sha256_prefix":"8d3d5f756818e024","entry":"uniform_loss","repo":"amazon-science/prompt-pretraining","repo_kind":"official","path":"align_uniform.py","file_url":"https://github.com/amazon-science/prompt-pretraining/blob/HEAD/align_uniform.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8d3d5f756818e024"}},{"code_sha256_prefix":"9542161e9640b858","entry":"whitespace_clean","repo":"amazon-science/prompt-pretraining","repo_kind":"official","path":"clip/simple_tokenizer.py","file_url":"https://github.com/amazon-science/prompt-pretraining/blob/HEAD/clip/simple_tokenizer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9542161e9640b858"}},{"code_sha256_prefix":"81ce35f8e245e82e","entry":"build_model","repo":"amazon-science/prompt-pretraining","repo_kind":"official","path":"clip/model.py","file_url":"https://github.com/amazon-science/prompt-pretraining/blob/HEAD/clip/model.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":true,"mcp_get_code":{"code_sha256":"81ce35f8e245e82e"}},{"code_sha256_prefix":"3776e3e7d4b86f52","entry":"load","repo":"amazon-science/prompt-pretraining","repo_kind":"official","path":"clip/clip.py","file_url":"https://github.com/amazon-science/prompt-pretraining/blob/HEAD/clip/clip.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":true,"mcp_get_code":{"code_sha256":"3776e3e7d4b86f52"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}