4 citations · 8 across the 7 of their papers we have counts for
8 papers
TTVD: Towards a Geometric Framework for Test-Time Adaptation Based on Voronoi Diagram
Mingxi Lei, Chunwei Ma, Meng Ding +3
Deep learning models often struggle with generalization when deploying on real-world data, due to the common distributional shift to the training data. Test-time adaptation (TTA) i…
Multiset Transformer: Advancing Representation Learning in Persistence Diagrams
Minghua Wang, Ziyun Huang, Jinhui Xu
To improve persistence diagram representation learning, we propose Multiset Transformer. This is the first neural network that utilizes attention mechanisms specifically designed f…
On Clustering Induced Voronoi Diagrams
Danny Z. Chen, Ziyun Huang, Yangwei Liu +1
In this paper, we study a generalization of the classical Voronoi diagram, called clustering induced Voronoi diagram (CIVD). Different from the traditional model, CIVD takes as its…
Progressive Voronoi Diagram Subdivision: Towards A Holistic Geometric Framework for Exemplar-free Class-Incremental Learning
Chunwei Ma, Zhanghexuan Ji, Ziyun Huang +3
Exemplar-free Class-incremental Learning (CIL) is a challenging problem because rehearsing data from previous phases is strictly prohibited, causing catastrophic forgetting of Deep…
In-Range Farthest Point Queries and Related Problem in High Dimensions
Ziyun Huang, Jinhui Xu
Range-aggregate query is an important type of queries with numerous applications. It aims to obtain some structural information (defined by an aggregate function ) of the…
Few-shot Learning as Cluster-induced Voronoi Diagrams: A Geometric Approach
Chunwei Ma, Ziyun Huang, Mingchen Gao +1
Few-shot learning (FSL) is the process of rapid generalization from abundant base samples to inadequate novel samples. Despite extensive research in recent years, FSL is still not…
Improving Uncertainty Calibration of Deep Neural Networks via Truth Discovery and Geometric Optimization
Chunwei Ma, Ziyun Huang, Jiayi Xian +2
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 l…
Data Transfer Optimization Based on Offline Knowledge Discovery and Adaptive Real-time Sampling
MD S Q Zulkar Nine, Kemal Guner, Ziyun Huang +3
The amount of data moved over dedicated and non-dedicated network links increases much faster than the increase in the network capacity, but the current solutions fail to guarantee…