English

Class-Incremental Grouping Network for Continual Audio-Visual Learning

Computer Vision and Pattern Recognition 2023-09-12 v1 Machine Learning Multimedia

Abstract

Continual learning is a challenging problem in which models need to be trained on non-stationary data across sequential tasks for class-incremental learning. While previous methods have focused on using either regularization or rehearsal-based frameworks to alleviate catastrophic forgetting in image classification, they are limited to a single modality and cannot learn compact class-aware cross-modal representations for continual audio-visual learning. To address this gap, we propose a novel class-incremental grouping network (CIGN) that can learn category-wise semantic features to achieve continual audio-visual learning. Our CIGN leverages learnable audio-visual class tokens and audio-visual grouping to continually aggregate class-aware features. Additionally, it utilizes class tokens distillation and continual grouping to prevent forgetting parameters learned from previous tasks, thereby improving the model's ability to capture discriminative audio-visual categories. We conduct extensive experiments on VGGSound-Instruments, VGGSound-100, and VGG-Sound Sources benchmarks. Our experimental results demonstrate that the CIGN achieves state-of-the-art audio-visual class-incremental learning performance. Code is available at https://github.com/stoneMo/CIGN.

Keywords

Cite

@article{arxiv.2309.05281,
  title  = {Class-Incremental Grouping Network for Continual Audio-Visual Learning},
  author = {Shentong Mo and Weiguo Pian and Yapeng Tian},
  journal= {arXiv preprint arXiv:2309.05281},
  year   = {2023}
}

Comments

ICCV 2023. arXiv admin note: text overlap with arXiv:2303.17056

R2 v1 2026-06-28T12:17:44.990Z