3 papers
cs.CV2024
Conjugated Semantic Pool Improves OOD Detection with Pre-trained Vision-Language Models
Mengyuan Chen, Junyu Gao, Changsheng Xu
A straightforward pipeline for zero-shot out-of-distribution (OOD) detection involves selecting potential OOD labels from an extensive semantic pool and then leveraging a pre-train…
cs.LG2024
Revisiting Essential and Nonessential Settings of Evidential Deep Learning
Mengyuan Chen, Junyu Gao, Changsheng Xu
Evidential Deep Learning (EDL) is an emerging method for uncertainty estimation that provides reliable predictive uncertainty in a single forward pass, attracting significant atten…
cs.LG2024
A Comprehensive Survey on Evidential Deep Learning and Its Applications
Junyu Gao, Mengyuan Chen, Liangyu Xiang +1
Reliable uncertainty estimation has become a crucial requirement for the industrial deployment of deep learning algorithms, particularly in high-risk applications such as autonomou…