Angular Visual Hardness
Published in arXiv (Cornell University) • Dec 4, 2019
NobleIDNI4P82W32R96S72
Authors:,,
Beidi Chen
Weiyang Liu
Zhiding Yu
Abstract
Recent convolutional neural networks (CNNs) have led to impressive performance but often suffer from poor calibration. They tend to be overconfident, with the model confidence not always reflecting the underlying true ambiguity and hardness. In this paper, we propose angular visual hardness (AVH), a...
Subject
Finding related papers...
Discussions
(0)No comments yet
Be the first to share your thoughts!