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

Code

• github.com/google-research/vision_transformer
  OfficialIn paperjax★ 12,380
• github.com/google-research/big_vision
  OfficialIn paperjax★ 3,388
• github.com/mlfoundations/open_clip
  pytorch★ 13,551
• github.com/laion-ai/clip_benchmark
  pytorch★ 808
• github.com/eify/clip_benchmark
  pytorch★ 0

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.

Tasks

Benchmark Results

Reproductions