Feature Augmentation based Test-Time Adaptation

TL;DR

FATA introduces feature augmentation with normalization perturbation for test-time adaptation, enhancing model robustness in limited-data scenarios without changing model architecture.

Contribution

It proposes a simple, model-agnostic feature augmentation method for TTA that improves adaptation under data constraints by utilizing normalization perturbation.

Findings

FATA outperforms existing TTA methods on ImageNet-C.

FATA improves accuracy on Office-Home dataset.

FATA is compatible with various models.

Abstract

Test-time adaptation (TTA) allows a model to be adapted to an unseen domain without accessing the source data. Due to the nature of practical environments, TTA has a limited amount of data for adaptation. Recent TTA methods further restrict this by filtering input data for reliability, making the effective data size even smaller and limiting adaptation potential. To address this issue, We propose Feature Augmentation based Test-time Adaptation (FATA), a simple method that fully utilizes the limited amount of input data through feature augmentation. FATA employs Normalization Perturbation to augment features and adapts the model using the FATA loss, which makes the outputs of the augmented and original features similar. FATA is model-agnostic and can be seamlessly integrated into existing models without altering the model architecture. We demonstrate the effectiveness of FATA on various models and scenarios on ImageNet-C and Office-Home, validating its superiority in diverse real-world conditions.