Progressive Voronoi Diagram Subdivision: Towards A Holistic Geometric Framework for Exemplar-free Class-Incremental Learning

no code implementations • 28 Jul 2022 • Chunwei Ma, Zhanghexuan Ji, Ziyun Huang, Yan Shen, Mingchen Gao, Jinhui Xu

Exemplar-free Class-incremental Learning (CIL) is a challenging problem because rehearsing data from previous phases is strictly prohibited, causing catastrophic forgetting of Deep Neural Networks (DNNs).

Class Incremental Learning Incremental Learning +1

Few-shot Learning as Cluster-induced Voronoi Diagrams: A Geometric Approach

1 code implementation • 5 Feb 2022 • Chunwei Ma, Ziyun Huang, Mingchen Gao, Jinhui Xu

One observation is that the widely embraced ProtoNet model is essentially a Voronoi Diagram (VD) in the feature space.

Few-Shot Learning

Few-shot Learning via Dirichlet Tessellation Ensemble

no code implementations • ICLR 2022 • Chunwei Ma, Ziyun Huang, Mingchen Gao, Jinhui Xu

One observation is that the widely embraced ProtoNet model is essentially a Dirichlet Tessellation (Voronoi Diagram) in the feature space.

Few-Shot Learning

Improving Uncertainty Calibration of Deep Neural Networks via Truth Discovery and Geometric Optimization

1 code implementation • 25 Jun 2021 • Chunwei Ma, Ziyun Huang, Jiayi Xian, Mingchen Gao, Jinhui Xu

Deep Neural Networks (DNNs), despite their tremendous success in recent years, could still cast doubts on their predictions due to the intrinsic uncertainty associated with their learning process.