93 citations · 215 across the 13 of their papers we have counts for
14 papers
Topology-Adaptive Hyperbolic Graph Attention Networks Guided by the Hyperbolic Sombor Index
Haifang Cao, Boan Tao, Xiyuan Gao +3
Hyperbolic geometry has emerged as a principled space for representing hierarchical graphs. However, existing hyperbolic graph neural networks typically rely on shared curvature co…
Geometric Mixture-of-Experts with Curvature-Guided Adaptive Routing for Graph Representation Learning
Haifang Cao, Yu Wang, Timing Li +2
Graph-structured data typically exhibits complex topological heterogeneity, making it difficult to model accurately within a single Riemannian manifold. While emerging mixed-curvat…
BackMix: Regularizing Open Set Recognition by Removing Underlying Fore-Background Priors
Yu Wang, Junxian Mu, Hongzhi Huang +3
Open set recognition (OSR) requires models to classify known samples while detecting unknown samples for real-world applications. Existing studies show impressive progress using un…
Reducing Class-wise Confusion for Incremental Learning with Disentangled Manifolds
Huitong Chen, Yu Wang, Yan Fan +2
Class incremental learning (CIL) aims to enable models to continuously learn new classes without catastrophically forgetting old ones. A promising direction is to learn and use pro…
CKD: Contrastive Knowledge Distillation from A Sample-wise Perspective
Wencheng Zhu, Xin Zhou, Pengfei Zhu +2
In this paper, we propose a simple yet effective contrastive knowledge distillation framework that achieves sample-wise logit alignment while preserving semantic consistency. Conve…
Every Node is Different: Dynamically Fusing Self-Supervised Tasks for Attributed Graph Clustering
Pengfei Zhu, Qian Wang, Yu Wang +2
Attributed graph clustering is an unsupervised task that partitions nodes into different groups. Self-supervised learning (SSL) shows great potential in handling this task, and som…
Exploring Diverse Representations for Open Set Recognition
Yu Wang, Junxian Mu, Pengfei Zhu +1
Open set recognition (OSR) requires the model to classify samples that belong to closed sets while rejecting unknown samples during test. Currently, generative models often perform…
Dynamic Sub-graph Distillation for Robust Semi-supervised Continual Learning
Yan Fan, Yu Wang, Pengfei Zhu +1
Continual learning (CL) has shown promising results and comparable performance to learning at once in a fully supervised manner. However, CL strategies typically require a large nu…
Latent Heterogeneous Graph Network for Incomplete Multi-View Learning
Pengfei Zhu, Xinjie Yao, Yu Wang +4
Multi-view learning has progressed rapidly in recent years. Although many previous studies assume that each instance appears in all views, it is common in real-world applications f…
Class-Specific Semantic Reconstruction for Open Set Recognition
Hongzhi Huang, Yu Wang, Qinghua Hu +1
Open set recognition enables deep neural networks (DNNs) to identify samples of unknown classes, while maintaining high classification accuracy on samples of known classes. Existin…
Multi-Granularity Regularized Re-Balancing for Class Incremental Learning
Huitong Chen, Yu Wang, Qinghua Hu
Deep learning models suffer from catastrophic forgetting when learning new tasks incrementally. Incremental learning has been proposed to retain the knowledge of old classes while…
Learning Self-Supervised Low-Rank Network for Single-Stage Weakly and Semi-Supervised Semantic Segmentation
Junwen Pan, Pengfei Zhu, Kaihua Zhang +5
Semantic segmentation with limited annotations, such as weakly supervised semantic segmentation (WSSS) and semi-supervised semantic segmentation (SSSS), is a challenging task that…
Learning Dynamic Compact Memory Embedding for Deformable Visual Object Tracking
Pengfei Zhu, Hongtao Yu, Kaihua Zhang +5
Recently, template-based trackers have become the leading tracking algorithms with promising performance in terms of efficiency and accuracy. However, the correlation operation bet…
Expert Training: Task Hardness Aware Meta-Learning for Few-Shot Classification
Yucan Zhou, Yu Wang, Jianfei Cai +3
Deep neural networks are highly effective when a large number of labeled samples are available but fail with few-shot classification tasks. Recently, meta-learning methods have rec…