Skip to yearly menu bar Skip to main content


Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models

Manli Shu · Weili Nie · De-An Huang · Zhiding Yu · Tom Goldstein · Anima Anandkumar · Chaowei Xiao

Hall J (level 1) #633

Keywords: [ Foundation Model ] [ Prompt Tuning ] [ Out-of-Distribution Robustness ] [ generalization ]


Pre-trained vision-language models (e.g., CLIP) have shown promising zero-shot generalization in many downstream tasks with properly designed text prompts. Instead of relying on hand-engineered prompts, recent works learn prompts using the training data from downstream tasks. While effective, training on domain-specific data reduces a model's generalization capability to unseen new domains. In this work, we propose test-time prompt tuning (TPT), a method that can learn adaptive prompts on the fly with a single test sample. TPT optimizes the prompt by minimizing the entropy with confidence selection so that the model has consistent predictions across different augmented views of each test sample. In evaluating generalization to natural distribution shifts, TPT improves the zero-shot top-1 accuracy of CLIP by 3.6\% on average, surpassing previous prompt tuning approaches that require additional task-specific training data. In evaluating cross-dataset generalization with unseen categories, TPTperforms on par with the state-of-the-art approaches that use additional training data.

Chat is not available.