Efficient Test-Time Adaptation of Vision-Language Models

arXiv:2403.18293v1 Announce Type: new
Abstract: Test-time adaptation with pre-trained vision-language models has attracted increasing attention for tackling distribution shifts during the test time. Though prior studies have achieved very promising performance, they involve intensive computation which is severely unaligned with test-time adaptation. We design TDA, a training-free dynamic adapter that enables effective and efficient test-time adaptation with vision-language models. TDA works with a lightweight key-value cache that maintains a dynamic queue with few-shot pseudo labels as values and the corresponding …

arxiv cs.cv language language models test type vision vision-language models