Continual Evidential Deep Learning for Out-of-Distribution Detection
Uncertainty-based deep learning models have attracted a great deal of interest for their
ability to provide accurate and reliable predictions. Evidential deep learning stands out …
ability to provide accurate and reliable predictions. Evidential deep learning stands out …
Beyond uncertainty: Evidential deep learning for robust video temporal grounding
Existing Video Temporal Grounding (VTG) models excel in accuracy but often overlook open-
world challenges posed by open-vocabulary queries and untrimmed videos. This leads to …
world challenges posed by open-vocabulary queries and untrimmed videos. This leads to …
Towards Robust Uncertainty-Aware Incomplete Multi-View Classification
M Chen, H Huang, Q Li - arXiv preprint arXiv:2409.06270, 2024 - arxiv.org
Handling incomplete data in multi-view classification is challenging, especially when
traditional imputation methods introduce biases that compromise uncertainty estimation …
traditional imputation methods introduce biases that compromise uncertainty estimation …
Duedl: Dual-Branch Evidential Deep Learning for Weakly Supervised Medical Image Segmentation Via Scribble Annotations
Despite recent advances in weakly supervised medical image segmentation using scribble
annotations, most models still lack robustness and generalizability in open environments …
annotations, most models still lack robustness and generalizability in open environments …