Video Test-Time Adaptation for Action Recognition

TL;DR

This paper introduces a test-time adaptation method for video action recognition that aligns feature distributions and enforces prediction consistency, significantly improving performance under distribution shifts.

Contribution

It presents a novel, architecture-agnostic test-time adaptation technique tailored for spatio-temporal models in video action recognition.

Findings

Significant performance boost on benchmark datasets.

Effective on both convolutional and transformer architectures.

Outperforms existing test-time adaptation methods.

Abstract

Although action recognition systems can achieve top performance when evaluated on in-distribution test points, they are vulnerable to unanticipated distribution shifts in test data. However, test-time adaptation of video action recognition models against common distribution shifts has so far not been demonstrated. We propose to address this problem with an approach tailored to spatio-temporal models that is capable of adaptation on a single video sample at a step. It consists in a feature distribution alignment technique that aligns online estimates of test set statistics towards the training statistics. We further enforce prediction consistency over temporally augmented views of the same test video sample. Evaluations on three benchmark action recognition datasets show that our proposed technique is architecture-agnostic and able to significantly boost the performance on both, the state of the art convolutional architecture TANet and the Video Swin Transformer. Our proposed method demonstrates a substantial performance gain over existing test-time adaptation approaches in both evaluations of a single distribution shift and the challenging case of random distribution shifts. Code will be available at \url{https://github.com/wlin-at/ViTTA}.