DeepAI AI Chat
Log In Sign Up

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

by   Kazuki Adachi, et al.

The accuracy of deep neural networks is degraded when the distribution of features in the test environment (target domain) differs from that of the training (source) environment. To mitigate the degradation, test-time adaptation (TTA), where a model adapts to the target domain without access to the source dataset, can be used in the test environment. However, the existing TTA methods lack feature distribution alignment between the source and target domains, which unsupervised domain adaptation mainly addresses, because accessing the source dataset is prohibited in the TTA setting. In this paper, we propose a novel TTA method, named Covariance-Aware Feature alignment (CAFe), which explicitly aligns the source and target feature distributions at test time. To perform alignment without accessing the source data, CAFe uses auxiliary feature statistics (mean and covariance) pre-computed on the source domain, which are lightweight and easily prepared. Further, to improve efficiency and stability, we propose feature grouping, which splits the feature dimensions into groups according to their correlations by using spectral clustering to avoid degeneration of the covariance matrix. We empirically show that CAFe outperforms prior TTA methods on a variety of distribution shifts.


page 14

page 15


Co-regularized Alignment for Unsupervised Domain Adaptation

Deep neural networks, trained with large amount of labeled data, can fai...

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

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

Improving Test-Time Adaptation via Shift-agnostic Weight Regularization and Nearest Source Prototypes

This paper proposes a novel test-time adaptation strategy that adjusts t...

Feature Alignment and Uniformity for Test Time Adaptation

Test time adaptation (TTA) aims to adapt deep neural networks when recei...

A Joint Pixel and Feature Alignment Framework for Cross-dataset Palmprint Recognition

Deep learning-based palmprint recognition algorithms have shown great po...

Revisiting Realistic Test-Time Training: Sequential Inference and Adaptation by Anchored Clustering

Deploying models on target domain data subject to distribution shift req...