Mixup-Inspired Video Class-Incremental Learning

Continual learning aims to learn a sequence of tasks without forgetting the previously learned knowledge. Although existing memory-based approaches can he easily deployed for video Class-Incremental Learning (CIL), little efforts have been made to explore how to better exploit the data from the previous work (in the memory) for alleviating the catastrophic forgetting. In this work, we thus propose a simple yet effective framework called Mixup-Inspired Video Class-Incremental Learning (MIVCIL). The core idea of our MINIM. framework is to impose mixup on the current video data and the previous video data (from the memory buffer) to mitigate the catastrophic forgetting. By exploring different mixup strategies on the video data, our MIVCIL framework has three instantiations for video classTemental learning. We further provide a detailed analysis of the performance and computational overhead of the three instantiations on the latest benchmark vCIAMB. Experimental results show that all three instantiations achieve significant improvements over the representative/state-of-the-art methods.