</> Code with Papers by Syntology

Papers › LiT: Zero-Shot Transfer with Locked-image text Tuning

LiT: Zero-Shot Transfer with Locked-image text Tuning

15 Nov 2021CVPR 2022 1arXiv:2111.07991archive 2025-07-28

Xiaohua Zhai, Xiao Wang, Basil Mustafa, Andreas Steiner, Daniel Keysers, Alexander Kolesnikov, Lucas Beyer

This paper presents contrastive-tuning, a simple method employing contrastive training to align image and text models while still taking advantage of their pre-training. In our empirical study we find that locked pre-trained image models with unlocked text models work best. We call this instance of contrastive-tuning "Locked-image Tuning" (LiT), which just teaches a text model to read out good representations from a pre-trained image model for new tasks. A LiT model gains the capability of zero-shot transfer to new vision tasks, such as image classification or retrieval. The proposed LiT is widely applicable; it works reliably with multiple pre-training methods (supervised and unsupervised) and across diverse architectures (ResNet, Vision Transformers and MLP-Mixer) using three different image-text datasets. With the transformer-based pre-trained ViT-g/14 model, the LiT model achieves 85.2% zero-shot transfer accuracy on the ImageNet test set, and 82.5% on the challenging out-of-distribution ObjectNet test set.

PaperPDFConference PDFCode

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

Code

google-research/big_vision officialmentioned in papermentioned on GitHubjax report
google-research/vision_transformer officialmentioned in papermentioned on GitHubjax report
eify/clip_benchmark mentioned on GitHubpytorchMIT report
laion-ai/clip_benchmark mentioned on GitHubpytorchMIT report
mlfoundations/open_clip 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

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image ClassificationRetrievalZero-Shot Image ClassificationZero-Shot Transfer Image Classificationimage-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification ObjectNet LiT Top-1 Accuracy 82.5 #2 of 106 Archive leaderboard report
Zero-Shot Transfer Image Classification ImageNet LiT-tuning Accuracy (Private) 84.5 #7 of 23 Archive leaderboard report
Zero-Shot Transfer Image Classification ImageNet LiT-tuning Accuracy (Public) 75.7 #7 of 23 Archive leaderboard report
Zero-Shot Transfer Image Classification ImageNet ReaL LiT-tuning Accuracy (Private) 88.0 #1 of 1 Archive leaderboard report
Zero-Shot Transfer Image Classification ImageNet ReaL LiT-tuning Accuracy (Public) 82.2 #1 of 1 Archive leaderboard report
Zero-Shot Transfer Image Classification ImageNet V2 LiT-tuning Accuracy (Private) 78.7 #6 of 13 Archive leaderboard report
Zero-Shot Transfer Image Classification ImageNet V2 LiT-tuning Accuracy (Public) 66.6 #6 of 13 Archive leaderboard report
Zero-Shot Transfer Image Classification ImageNet-A LiT-tuning Accuracy (Private) 79.4 #9 of 13 Archive leaderboard report
Zero-Shot Transfer Image Classification ImageNet-A LiT-tuning Accuracy (Public) 37.8 #9 of 13 Archive leaderboard report
Zero-Shot Transfer Image Classification ImageNet-R LiT-tuning Accuracy 93.9 #8 of 12 Archive leaderboard report
Zero-Shot Transfer Image Classification ObjectNet LiT-tuning Accuracy (Private) 81.1 #5 of 9 Archive leaderboard report
Zero-Shot Transfer Image Classification ObjectNet LiT-tuning Accuracy (Public) 54.5 #5 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.

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