3 papers
cs.CV2024
DPU: Dynamic Prototype Updating for Multimodal Out-of-Distribution Detection
Shawn Li, Huixian Gong, Hao Dong +3
Out-of-distribution (OOD) detection is essential for ensuring the robustness of machine learning models by identifying samples that deviate from the training distribution. While tr…
cs.CV2024
MultiOOD: Scaling Out-of-Distribution Detection for Multiple Modalities
Hao Dong, Yue Zhao, Eleni Chatzi +1
Detecting out-of-distribution (OOD) samples is important for deploying machine learning models in safety-critical applications such as autonomous driving and robot-assisted surgery…
cs.LG2024
NNG-Mix: Improving Semi-supervised Anomaly Detection with Pseudo-anomaly Generation
Hao Dong, Gaëtan Frusque, Yue Zhao +2
Anomaly detection (AD) is essential in identifying rare and often critical events in complex systems, finding applications in fields such as network intrusion detection, financial…