A Lost Opportunity for Vision-Language Models: A Comparative Study of Online Test-time Adaptation for Vision-Language Models

In the realm of deep learning, maintaining model robustness against distribution shifts is critical. This paper investigates test-time adaptation strategies for vision-language models, with a specific focus on CLIP and its variants. Through a systematic exploration of prompt-based techniques and existing test-time adaptation methods, the study aims to enhance the adaptability and robustness of vision-language models in diverse real-world scenarios. The investigation includes an analysis of prompt engineering strategies, such as hand-crafted prompts, prompt ensembles, and prompt learning techniques. We introduce a vision-text-space ensemble that significantly boosts the average performance compared to a text-space-only ensemble. Additionally, our comparative study explore leveraging existing test-time adaptation methods originally designed for image classification tasks. Experimental evaluations conducted across various datasets and model architectures demonstrate the efficacy of different adaptation strategies. We further give insights into the importance of updating the vision encoder and whether it is beneficial to update the text encoder. Code is available at https://github.com/mariodoebler/test-time-adaptation