Video Test-Time Adaptation for Action Recognition
This addresses the challenge of adapting video action recognition models to unanticipated distribution shifts during testing, which is an incremental improvement for enhancing robustness in real-world applications.
The paper tackles the problem of action recognition models being vulnerable to distribution shifts in test data by proposing a test-time adaptation method tailored to spatio-temporal models, which significantly boosts performance on benchmark datasets, achieving substantial gains over existing approaches.
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}.