Junyuan Hong
Junyuan Hong
Research
Publications
Experiences
Teaching
OoD detection
Turning the Curse of Heterogeneity in Federated Learning into a Blessing for Out-of-Distribution Detection
Deep neural networks have witnessed huge successes in many challenging prediction tasks and yet they often suffer from out-of-distribution (OoD) samples, misclassifying them with high confidence. Recent advances show promising OoD detection …
Cite
×