Evidential active recognition: Intelligent and prudent open-world embodied perception

L Fan, M Liang, Y Li, G Hua… - Proceedings of the IEEE …, 2024 - openaccess.thecvf.com
Active recognition enables robots to intelligently explore novel observations thereby
acquiring more information while circumventing undesired viewing conditions. Recent …

Weakly-supervised residual evidential learning for multi-instance uncertainty estimation

P Liu, L Ji - arxiv preprint arxiv:2405.04405, 2024 - arxiv.org
Uncertainty estimation (UE), as an effective means of quantifying predictive uncertainty, is
crucial for safe and reliable decision-making, especially in high-risk scenarios. Existing UE …

Revisiting Essential and Nonessential Settings of Evidential Deep Learning

M Chen, J Gao, C Xu - arxiv preprint arxiv:2410.00393, 2024 - arxiv.org
Evidential Deep Learning (EDL) is an emerging method for uncertainty estimation that
provides reliable predictive uncertainty in a single forward pass, attracting significant …

Trustworthy Behavior Modeling and Decision Making for Autonomous Driving

R Jiao - 2024 - search.proquest.com
Recent advances in deep learning have significantly propelled the development of
autonomous vehicles. However, these systems face critical challenges in system-level …

Active Visual Recognition in Open World

L Fan - 2024 - search.proquest.com
Visual recognition, a core area of computer vision, aims to interpret semantic information
from images and videos. With advancements in deep neural networks and substantial …