{"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/lit-zero-shot-transfer-with-locked-image-text","title":"LiT: Zero-Shot Transfer with Locked-image text Tuning","arxiv_id":"2111.07991","date":"2021-11-15","proceeding":"CVPR 2022 1","authors":["Xiaohua Zhai","Xiao Wang","Basil Mustafa","Andreas Steiner","Daniel Keysers","Alexander Kolesnikov","Lucas Beyer"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2111.07991v3","url_pdf":"https://arxiv.org/pdf/2111.07991v3.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":"lit-zero-shot-transfer-with-locked-image-text","repo_url":"https://github.com/google-research/big_vision","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":null},{"paper_slug":"lit-zero-shot-transfer-with-locked-image-text","repo_url":"https://github.com/google-research/vision_transformer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":null},{"paper_slug":"lit-zero-shot-transfer-with-locked-image-text","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":"lit-zero-shot-transfer-with-locked-image-text","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"}},{"paper_slug":"lit-zero-shot-transfer-with-locked-image-text","repo_url":"https://github.com/mlfoundations/open_clip","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"zero-shot-image-classification","task_name":"Zero-Shot Image Classification"},{"task_slug":"zero-shot-transfer-image-classification","task_name":"Zero-Shot Transfer Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-objectnet","task":"Image Classification","dataset":"ObjectNet","model":"LiT","rank_in_archive_order":2,"of":106,"metrics":{"Top-1 Accuracy":"82.5"},"uses_additional_data":true},{"leaderboard":"/sota/zero-shot-transfer-image-classification-on-1","task":"Zero-Shot Transfer Image Classification","dataset":"ImageNet","model":"LiT-tuning","rank_in_archive_order":7,"of":23,"metrics":{"Accuracy (Private)":"84.5","Accuracy (Public)":"75.7"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-transfer-image-classification-on-7","task":"Zero-Shot Transfer Image Classification","dataset":"ImageNet ReaL","model":"LiT-tuning","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy (Private)":"88.0","Accuracy (Public)":"82.2"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-transfer-image-classification-on-3","task":"Zero-Shot Transfer Image Classification","dataset":"ImageNet V2","model":"LiT-tuning","rank_in_archive_order":6,"of":13,"metrics":{"Accuracy (Private)":"78.7","Accuracy (Public)":" 66.6"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-transfer-image-classification-on-5","task":"Zero-Shot Transfer Image Classification","dataset":"ImageNet-A","model":"LiT-tuning","rank_in_archive_order":9,"of":13,"metrics":{"Accuracy (Private)":"79.4","Accuracy (Public)":" 37.8"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-transfer-image-classification-on-4","task":"Zero-Shot Transfer Image Classification","dataset":"ImageNet-R","model":"LiT-tuning","rank_in_archive_order":8,"of":12,"metrics":{"Accuracy":"93.9"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-transfer-image-classification-on-6","task":"Zero-Shot Transfer Image Classification","dataset":"ObjectNet","model":"LiT-tuning","rank_in_archive_order":5,"of":9,"metrics":{"Accuracy (Private)":"81.1","Accuracy (Public)":" 54.5"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2111.07991","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}