Multi-Step Test-Time Adaptation with Entropy Minimization and Pseudo-Labeling

The accuracy of deep neural networks is easily degraded by image corruption. Therefore, there is a need to develop adaptation techniques to ensure durable models and predictions against changes in data distribution. We focus on the task to fit a trained model with a different distribution from training data under the condition that the training data are not available for test time. In this paper, we propose a novel adaptation method in test time for online learning named multi-step layer adaptation (MuSLA). The proposed method achieves high adaptive accuracy by sequentially applying loss functions to specific layers only, especially considering the roles and inter-actions of the layers and employing domain adaptation and semi-supervised learning techniques. The proposed method can be widely applied to already existing trained models with-out additional networks. We show that our approach outperforms conventional methods in image corruption benchmark data experiments.