Using Semantic Information for Defining and Detecting OOD Inputs

no code implementations • 21 Feb 2023 • Ramneet Kaur, Xiayan Ji, Souradeep Dutta, Michele Caprio, Yahan Yang, Elena Bernardis, Oleg Sokolsky, Insup Lee

This can render the current OOD detectors impermeable to inputs lying outside the training distribution but with the same semantic information (e. g. training class labels).

Anomaly Detection Out of Distribution (OOD) Detection

PAC-Wrap: Semi-Supervised PAC Anomaly Detection

no code implementations • 22 May 2022 • Shuo Li, Xiayan Ji, Edgar Dobriban, Oleg Sokolsky, Insup Lee

Anomaly detection is essential for preventing hazardous outcomes for safety-critical applications like autonomous driving.

Autonomous Driving Unsupervised Anomaly Detection

Towards PAC Multi-Object Detection and Tracking

no code implementations • 15 Apr 2022 • Shuo Li, Sangdon Park, Xiayan Ji, Insup Lee, Osbert Bastani

Accurately detecting and tracking multi-objects is important for safety-critical applications such as autonomous navigation.

Autonomous Navigation Conformal Prediction +3