Papers › EVA-CLIP: Improved Training Techniques for CLIP at Scale

EVA-CLIP: Improved Training Techniques for CLIP at Scale

27 Mar 2023arXiv:2303.15389archive 2025-07-28

Quan Sun, Yuxin Fang, Ledell Wu, Xinlong Wang, Yue Cao

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.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2303.15389")

Code

Syntology Ran 0 of 4 code samples harvested from 1 repository linked to this paper; 4 have no recorded run.

By repository: community (archive-listed): 4 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

baaivision/eva officialmentioned in paperpytorchMIT report
Yui010206/CREMA mentioned on GitHubpytorchBSD-3-Clause report
jaehong31/raccoon mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

4 samples harvested; 0 ran; 0 honoured the contract we drafted; 4 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

4unverified

Licence: 0 of the 4 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from PaddlePaddle/PaddleMIX. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

create_ui PaddlePaddle/PaddleMIX/paddlemix/MULLM_WebUI/interface.py community (archive-listed) unverified Apache-2.0 (permissive) · 00373b30be1d98cd · report
get_model_info PaddlePaddle/PaddleMIX/paddlemix/MULLM_WebUI/common.py community (archive-listed) unverified Apache-2.0 (permissive) · f523f7dc0633013b · report
get_model_path PaddlePaddle/PaddleMIX/paddlemix/MULLM_WebUI/common.py community (archive-listed) unverified Apache-2.0 (permissive) · ac470b0ec166399d · report
get_template PaddlePaddle/PaddleMIX/paddlemix/MULLM_WebUI/common.py community (archive-listed) unverified Apache-2.0 (permissive) · 903eaa561fc807bb · report

Tasks

Image ClassificationRepresentation LearningZero-Shot Action RecognitionZero-Shot Transfer Image Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification ObjectNet EVA-02-CLIP-E/14+ Top-1 Accuracy 79.6 #4 of 106 Archive leaderboard report
Zero-Shot Action Recognition UCF101 EVA-CLIP-E/14+ Top-1 Accuracy 83.1 #8 of 35 Archive leaderboard report
Zero-Shot Transfer Image Classification Food-101 EVA-CLIP-E/14+ Top 1 Accuracy 94.9 #4 of 5 Archive leaderboard report
Zero-Shot Transfer Image Classification ImageNet EVA-CLIP-E/14+ Accuracy (Private) 82 #12 of 23 Archive leaderboard report
Zero-Shot Transfer Image Classification ImageNet V2 EVA-CLIP-E/14+ Accuracy (Private) 75.7 #9 of 13 Archive leaderboard report
Zero-Shot Transfer Image Classification ImageNet-A EVA-CLIP-E/14+ Accuracy (Private) 82.1 #8 of 13 Archive leaderboard report
Zero-Shot Transfer Image Classification ImageNet-R EVA-CLIP-E/14+ Accuracy 94.5 #7 of 12 Archive leaderboard report
Zero-Shot Transfer Image Classification ImageNet-Sketch EVA-CLIP-E/14+ Accuracy (Private) 71.6 #6 of 7 Archive leaderboard report
Zero-Shot Transfer Image Classification ObjectNet EVA-CLIP-E/14+ Accuracy (Private) 79.6 #7 of 9 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

CLIP

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections