DeepAI AI Chat
Log In Sign Up

Feature Alignment and Uniformity for Test Time Adaptation

by   Shuai Wang, et al.
Southern University of Science & Technology
Tsinghua University
Hong Kong Polytechnic University

Test time adaptation (TTA) aims to adapt deep neural networks when receiving out of distribution test domain samples. In this setting, the model can only access online unlabeled test samples and pre-trained models on the training domains. We first address TTA as a feature revision problem due to the domain gap between source domains and target domains. After that, we follow the two measurements alignment and uniformity to discuss the test time feature revision. For test time feature uniformity, we propose a test time self-distillation strategy to guarantee the consistency of uniformity between representations of the current batch and all the previous batches. For test time feature alignment, we propose a memorized spatial local clustering strategy to align the representations among the neighborhood samples for the upcoming batch. To deal with the common noisy label problem, we propound the entropy and consistency filters to select and drop the possible noisy labels. To prove the scalability and efficacy of our method, we conduct experiments on four domain generalization benchmarks and four medical image segmentation tasks with various backbones. Experiment results show that our method not only improves baseline stably but also outperforms existing state-of-the-art test time adaptation methods.


page 1

page 2

page 3

page 4


CAFA: Class-Aware Feature Alignment for Test-Time Adaptation

Despite recent advancements in deep learning, deep networks still suffer...

Covariance-aware Feature Alignment with Pre-computed Source Statistics for Test-time Adaptation

The accuracy of deep neural networks is degraded when the distribution o...

Robustifying Vision Transformer without Retraining from Scratch by Test-Time Class-Conditional Feature Alignment

Vision Transformer (ViT) is becoming more popular in image processing. S...

DETA: Denoised Task Adaptation for Few-Shot Learning

Test-time task adaptation in few-shot learning aims to adapt a pre-train...

CD-TTA: Compound Domain Test-time Adaptation for Semantic Segmentation

Test-time adaptation (TTA) has attracted significant attention due to it...

SATA: Source Anchoring and Target Alignment Network for Continual Test Time Adaptation

Adapting a trained model to perform satisfactorily on continually changi...

Energy-Based Test Sample Adaptation for Domain Generalization

In this paper, we propose energy-based sample adaptation at test time fo...