{"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/eva-clip-improved-training-techniques-for","title":"EVA-CLIP: Improved Training Techniques for CLIP at Scale","arxiv_id":"2303.15389","date":"2023-03-27","proceeding":null,"authors":["Quan Sun","Yuxin Fang","Ledell Wu","Xinlong Wang","Yue Cao"],"abstract":"Contrastive language-image pre-training, CLIP for short, has gained increasing attention for its potential in various scenarios. In this paper, we propose EVA-CLIP, a series of models that significantly improve the efficiency and effectiveness of CLIP training. Our approach incorporates new techniques for representation learning, optimization, and augmentation, enabling EVA-CLIP to achieve superior performance compared to previous CLIP models with the same number of parameters but significantly smaller training costs. Notably, our largest 5.0B-parameter EVA-02-CLIP-E/14+ with only 9 billion seen samples achieves 82.0 zero-shot top-1 accuracy on ImageNet-1K val. A smaller EVA-02-CLIP-L/14+ with only 430 million parameters and 6 billion seen samples achieves 80.4 zero-shot top-1 accuracy on ImageNet-1K val. To facilitate open access and open research, we release the complete suite of EVA-CLIP to the community at https://github.com/baaivision/EVA/tree/master/EVA-CLIP.","url_abs":"https://arxiv.org/abs/2303.15389v1","url_pdf":"https://arxiv.org/pdf/2303.15389v1.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":"eva-clip-improved-training-techniques-for","repo_url":"https://github.com/baaivision/eva","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"eva-clip-improved-training-techniques-for","repo_url":"https://github.com/Yui010206/CREMA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"eva-clip-improved-training-techniques-for","repo_url":"https://github.com/jaehong31/raccoon","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"eva-clip-improved-training-techniques-for","repo_url":"https://github.com/PaddlePaddle/PaddleMIX/tree/develop/paddlemix/examples","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":null}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"zero-shot-action-recognition","task_name":"Zero-Shot Action Recognition"},{"task_slug":"zero-shot-transfer-image-classification","task_name":"Zero-Shot Transfer Image Classification"}],"methods":[{"method_slug":"clip","method_name":"CLIP"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-objectnet","task":"Image Classification","dataset":"ObjectNet","model":"EVA-02-CLIP-E/14+","rank_in_archive_order":4,"of":106,"metrics":{"Top-1 Accuracy":"79.6"},"uses_additional_data":true},{"leaderboard":"/sota/zero-shot-action-recognition-on-ucf101","task":"Zero-Shot Action Recognition","dataset":"UCF101","model":"EVA-CLIP-E/14+","rank_in_archive_order":8,"of":35,"metrics":{"Top-1 Accuracy":"83.1"},"uses_additional_data":true},{"leaderboard":"/sota/zero-shot-transfer-image-classification-on-17","task":"Zero-Shot Transfer Image Classification","dataset":"Food-101","model":"EVA-CLIP-E/14+","rank_in_archive_order":4,"of":5,"metrics":{"Top 1 Accuracy":"94.9"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-transfer-image-classification-on-1","task":"Zero-Shot Transfer Image Classification","dataset":"ImageNet","model":"EVA-CLIP-E/14+","rank_in_archive_order":12,"of":23,"metrics":{"Accuracy (Private)":"82"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-transfer-image-classification-on-3","task":"Zero-Shot Transfer Image Classification","dataset":"ImageNet V2","model":"EVA-CLIP-E/14+","rank_in_archive_order":9,"of":13,"metrics":{"Accuracy (Private)":"75.7"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-transfer-image-classification-on-5","task":"Zero-Shot Transfer Image Classification","dataset":"ImageNet-A","model":"EVA-CLIP-E/14+","rank_in_archive_order":8,"of":13,"metrics":{"Accuracy (Private)":"82.1"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-transfer-image-classification-on-4","task":"Zero-Shot Transfer Image Classification","dataset":"ImageNet-R","model":"EVA-CLIP-E/14+","rank_in_archive_order":7,"of":12,"metrics":{"Accuracy":"94.5"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-transfer-image-classification-on-8","task":"Zero-Shot Transfer Image Classification","dataset":"ImageNet-Sketch","model":"EVA-CLIP-E/14+","rank_in_archive_order":6,"of":7,"metrics":{"Accuracy (Private)":"71.6"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-transfer-image-classification-on-6","task":"Zero-Shot Transfer Image Classification","dataset":"ObjectNet","model":"EVA-CLIP-E/14+","rank_in_archive_order":7,"of":9,"metrics":{"Accuracy (Private)":"79.6"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2303.15389","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.15389"}},"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/Yui010206/CREMA","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/baaivision/eva","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jaehong31/raccoon","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/PaddlePaddle/PaddleMIX/tree/develop/paddlemix/examples","reach":null}],"summary":{"unverified":4},"by_repo_kind":{"listed":{"samples":4,"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":0,"samples":[{"code_sha256_prefix":"00373b30be1d98cd","entry":"create_ui","repo":"PaddlePaddle/PaddleMIX","repo_kind":"listed","path":"paddlemix/MULLM_WebUI/interface.py","file_url":"https://github.com/PaddlePaddle/PaddleMIX/blob/HEAD/paddlemix/MULLM_WebUI/interface.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":"00373b30be1d98cd"}},{"code_sha256_prefix":"f523f7dc0633013b","entry":"get_model_info","repo":"PaddlePaddle/PaddleMIX","repo_kind":"listed","path":"paddlemix/MULLM_WebUI/common.py","file_url":"https://github.com/PaddlePaddle/PaddleMIX/blob/HEAD/paddlemix/MULLM_WebUI/common.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":"f523f7dc0633013b"}},{"code_sha256_prefix":"ac470b0ec166399d","entry":"get_model_path","repo":"PaddlePaddle/PaddleMIX","repo_kind":"listed","path":"paddlemix/MULLM_WebUI/common.py","file_url":"https://github.com/PaddlePaddle/PaddleMIX/blob/HEAD/paddlemix/MULLM_WebUI/common.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":"ac470b0ec166399d"}},{"code_sha256_prefix":"903eaa561fc807bb","entry":"get_template","repo":"PaddlePaddle/PaddleMIX","repo_kind":"listed","path":"paddlemix/MULLM_WebUI/common.py","file_url":"https://github.com/PaddlePaddle/PaddleMIX/blob/HEAD/paddlemix/MULLM_WebUI/common.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":"903eaa561fc807bb"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}