Multi-view class incremental learning

Depeng Li, Tianqi Wang, Junwei Chen, Kenji Kawaguchi, Cheng Lian, Zhigang Zeng

Abstract: Highlights•A novel multi-view class incremental learning paradigm is investigated.•Randomized representation learning ensures view-optimal working states.•Orthogonality fusion progressively integrates each newly collected view.•Selective weight consolidation alleviates catastrophic forgetting.