LiT: Zero-Shot Transfer with Locked-image text Tuning
This enables zero-shot transfer for vision tasks like classification and retrieval, but it is incremental as it builds on existing pre-trained models and contrastive methods.
The paper tackled the problem of zero-shot transfer to new vision tasks by aligning image and text models through contrastive training, achieving 85.2% accuracy on ImageNet and 82.5% on ObjectNet with a ViT-g/14 model.
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.