Continual Evidential Deep Learning for Out-of-Distribution Detection

E Aguilar, B Raducanu, P Radeva… - Proceedings of the …, 2023 - openaccess.thecvf.com
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 …

Beyond uncertainty: Evidential deep learning for robust video temporal grounding

K Ma, H Huang, J Chen, H Chen, P Ji, X Zang… - arXiv preprint arXiv …, 2024 - arxiv.org
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 …

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 …

Duedl: Dual-Branch Evidential Deep Learning for Weakly Supervised Medical Image Segmentation Via Scribble Annotations

X Xu, Y Yang, H Hu, Q Zhou, H Long… - Available at SSRN … - papers.ssrn.com
Despite recent advances in weakly supervised medical image segmentation using scribble
annotations, most models still lack robustness and generalizability in open environments …