Continual Learning: Forget-free Winning Subnetworks for Video Representations

Inspired by the Regularized Lottery Ticket Hypothesis (RLTH), which highlights the presence of competitive subnetworks within dense networks for continual learning tasks, we introduce Winning Subnetworks (WSN). This approach utilizes reused weights in dense networks to enhance learning in Task Incremental Learning (TIL) scenarios. To mitigate overfitting in Few-Shot Class Incremental Learning (FSCIL), we have developed WSN variants referred to as the Soft subnetwork (SoftNet). Furthermore, addressing WSN's limitation of sparse reused weights in Video Incremental Learning (VIL), we propose the Fourier Subneural Operator (FSO). The FSO, operating in Fourier space, adaptively and compactly encodes videos, discovering reusable subnetworks with diverse bandwidths. We have applied FSO's Fourier representations to various continual learning contexts, including VIL, TIL, and FSCIL. Our extensive experiments across these scenarios demonstrate FSO's remarkable efficacy in continual learning, significantly enhancing task performance at various convolutional representational levels: it boosts performance in the higher layers for TIL and FSCIL and the lower layers for VIL.