6 papers
Navigating Distribution Shifts in Medical Image Analysis: A Survey
Zixian Su, Jingwei Guo, Xi Yang +4
Medical Image Analysis (MedIA) has become indispensable in modern healthcare, enhancing clinical diagnostics and personalized treatment. Despite the remarkable advancements support…
Un-mixing Test-time Adaptation under Heterogeneous Data Streams
Zixian Su, Jingwei Guo, Xi Yang +2
Deploying deep models in real-world scenarios remains challenging due to significant performance drops under distribution shifts between training and deployment environments. Test-…
ES-GNN: Generalizing Graph Neural Networks Beyond Homophily with Edge Splitting
Jingwei Guo, Kaizhu Huang, Rui Zhang +1
While Graph Neural Networks (GNNs) have achieved enormous success in multiple graph analytical tasks, modern variants mostly rely on the strong inductive bias of homophily. However…
Rethinking Spectral Graph Neural Networks with Spatially Adaptive Filtering
Jingwei Guo, Kaizhu Huang, Xinping Yi +2
Whilst spectral Graph Neural Networks (GNNs) are theoretically well-founded in the spectral domain, their practical reliance on polynomial approximation implies a profound linkage…
Graph Neural Networks with Diverse Spectral Filtering
Jingwei Guo, Kaizhu Huang, Xinping Yi +1
Spectral Graph Neural Networks (GNNs) have achieved tremendous success in graph machine learning, with polynomial filters applied for graph convolutions, where all nodes share the…
Unraveling Batch Normalization for Realistic Test-Time Adaptation
Zixian Su, Jingwei Guo, Kai Yao +3
While recent test-time adaptations exhibit efficacy by adjusting batch normalization to narrow domain disparities, their effectiveness diminishes with realistic mini-batches due to…