Feiyang Cai

Real-time Out-of-distribution Detection in Learning-Enabled Cyber-Physical Systems

2020 · arXiv (Cornell University)

Cyber-physical systems (CPS) greatly benefit by using machine learning components that can handle the uncertainty and variability of the real-world. Typical components such as deep neural networks, however, introduce new types of hazards that may …

Open Set Recognition using Vision Transformer with an Additional Detection Head

2022 · arXiv (Cornell University)

Deep neural networks have demonstrated prominent capacities for image classification tasks in a closed set setting, where the test data come from the same distribution as the training data. However, in a more realistic open …