Gradient Alignment with Prototype Feature for Fully Test-time Adaptation
CoRR(2024)
摘要
In context of Test-time Adaptation(TTA), we propose a regularizer, dubbed
Gradient Alignment with Prototype feature (GAP), which alleviates the
inappropriate guidance from entropy minimization loss from misclassified pseudo
label. We developed a gradient alignment loss to precisely manage the
adaptation process, ensuring that changes made for some data don't negatively
impact the model's performance on other data. We introduce a prototype feature
of a class as a proxy measure of the negative impact. To make GAP regularizer
feasible under the TTA constraints, where model can only access test data
without labels, we tailored its formula in two ways: approximating prototype
features with weight vectors of the classifier, calculating gradient without
back-propagation. We demonstrate GAP significantly improves TTA methods across
various datasets, which proves its versatility and effectiveness.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要