视觉-语言模型的测试时对齐增强适配器
Test-time Alignment-Enhanced Adapter for Vision-Language Models
AI总结：
本文提出测试时对齐增强适配器TAEA，通过在测试阶段用测试样本训练适配器调整文本特征并结合负缓存，提升了预训练视觉-语言模型在分布外和跨域场景下的自适应性能。
摘要：
利用预训练视觉-语言模型（VLMs）进行测试时自适应，因解决测试阶段分布偏移问题而受到越来越多的关注。此前的方法通过调整分类 logits 在应对分布偏移方面已显示出有效性，但由于保持文本特征不变，它们并非最优。为解决这一问题，我们提出一种名为测试时对齐增强适配器（TAEA）的新方法，该方法在测试阶段利用测试样本训练一个适配器来调整文本特征。我们可以通过使用适配器来适应文本特征，从而增强文本到图像的对齐预测。此外，我们还提出采用 TDA 中的负缓存作为增强模块，进一步提升了 TAEA 的性能。我们的方法在分布外基准上平均优于预训练 VLM 的最先进 TTA 方法 0.75%，在跨域基准上平均优于 2.5%，且训练时间可接受。代码将发布于 https://github.com/BaoshunWq/clip-TAEA。
英文摘要：
Test-time adaptation with pre-trained vision-language models (VLMs) has attracted increasing attention for tackling the issue of distribution shift during the test phase. While prior methods have shown effectiveness in addressing distribution shift by adjusting classification logits, they are not optimal due to keeping text features unchanged. To address this issue, we introduce a new approach called Test-time Alignment-Enhanced Adapter (TAEA), which trains an adapter with test samples to adjust text features during the test phase. We can enhance the text-to-image alignment prediction by utilizing an adapter to adapt text features. Furthermore, we also propose to adopt the negative cache from TDA as enhancement module, which further improves the performance of TAEA. Our approach outperforms the state-of-the-art TTA method of pre-trained VLMs by an average of 0.75% on the out-of-distribution benchmark and 2.5% on the cross-domain benchmark, with an acceptable training time. Code will be available at https://github.com/BaoshunWq/clip-TAEA.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
