test-time adaptation (TTA) aims to adapt a pre-trained model to the target
domain in a batch-by-batch manner during inference. While label distributions
often exhibit imbalances in real-world scenarios, most previous TTA approaches
typically assume that both source and target domain da
本文研究了针对分布漂移进行测试时间自适应(TTA)的方法,在各种函数类中元学习 TTA loss 能够迅速获得与熵函数类似的 loss 函数,并基于最优 loss 函数提供了更好的 TTA 方法。同时,在新型的 supervised training loss 函数中,我们的方法也显示了优异的表现,为改善测试时间自适应提供了广阔的框架。