30 citations
- Shanghai Jiao Tong UniversityCN13 papers
- Shanghai Artificial Intelligence LaboratoryCN2 papers
- University of WashingtonUS2 papers
- Art Institute of PortlandUS1 paper
- Centre de Mathématiques Appliquées de l'École polytechniqueFR1 paper
- Chinese Academy of SciencesCN1 paper
- Cloud Computing CenterCN1 paper
- East China Normal UniversityCN1 paper
- École PolytechniqueFR1 paper
- Harvard UniversityUS1 paper
- Huawei Technologies (China)CN1 paper
- Huazhong University of Science and TechnologyCN1 paper
16 papers
Boundary-aware Supervoxel-level Iteratively Refined Interactive 3D Image Segmentation with Multi-agent Reinforcement Learning
Chaofan Ma, Qisen Xu, Xiangfeng Wang +4
Interactive segmentation has recently been explored to effectively and efficiently harvest high-quality segmentation masks by iteratively incorporating user hints. While iterative…
Discriminative Radial Domain Adaptation
Zenan Huang, Jun Wen, Siheng Chen +2
Domain adaptation methods reduce domain shift typically by learning domain-invariant features. Most existing methods are built on distribution matching, e.g., adversarial domain ad…
Integrating features from lymph node stations for metastatic lymph node detection
Chaoyi Wu, Feng Chang, Xiao Su +4
Metastasis on lymph nodes (LNs), the most common way of spread for primary tumor cells, is a sign of increased mortality. However, metastatic LNs are time-consuming and challenging…
Eruptions from coronal bright points: A spectroscopic view by IRIS of a mini-filament eruption, QSL reconnection, and reconnection-driven outflows
Maria S. Madjarska, Duncan H. Mackay, Klaus Galsgaard +2
The present study investigates a mini-filament eruption associated with cancelling magnetic fluxes. The eruption originates from a small-scale loop complex commonly known as a Coro…
Cooperative Learning for Noisy Supervision
Hao Wu, Jiangchao Yao, Ya Zhang +1
Learning with noisy labels has gained the enormous interest in the robust deep learning area. Recent studies have empirically disclosed that utilizing dual networks can enhance the…
A Fourier-based Framework for Domain Generalization
Qinwei Xu, Ruipeng Zhang, Ya Zhang +2
Modern deep neural networks suffer from performance degradation when evaluated on testing data under different distributions from training data. Domain generalization aims at tackl…