Video Test-Time Adaptation for Action Recognition
Authors:
Preprint
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}.Keywords
All Related Versions
This publication has 27 references indexed in Scilit:
- Spatiotemporal Self-attention Modeling with Temporal Patch Shift for Action Recognition2022
- Continual Test-Time Domain Adaptation2022
- ACTION-Net: Multipath Excitation for Action Recognition2021
- TDN: Temporal Difference Networks for Efficient Action Recognition2021
- X3D: Expanding Architectures for Efficient Video Recognition2020
- TEA: Temporal Excitation and Aggregation for Action Recognition2020
- Temporal Pyramid Network for Action Recognition2020
- Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset2017
- Temporal Segment Networks: Towards Good Practices for Deep Action Recognition2016
- Deep Residual Learning for Image Recognition2016