Stanford Cars

Researchers proposed DART-FL, a burst-aware multitask federated learning framework that dynamically splits resources between inference and training to meet service-level objectives under time-varying …

Researchers present Subtoken Vision Transformer (SubViT), a selective image tokenization method that improves fine-grained visual recognition by representing discriminative patches with multiple subto…

Researchers propose vMFProto, a distributional part-prototype framework that models each class as a mixture of von Mises-Fisher components on the hypersphere for interpretable classification. The meth…