期刊
PATTERN RECOGNITION
卷 105, 期 -, 页码 -出版社
ELSEVIER SCI LTD
DOI: 10.1016/j.patcog.2020.107202
关键词
Interpretability; Hand detection; Pixel level; Explainable representation; Rotation map
资金
- National Natural Science Foundation of China [6180/033]
- Key Research Program of Frontier Sciences, CAS [ZDBS-LY-JSC038]
- Youth Innovation Promotion Association, CAS [2020111]
- Outstanding Youth Scientist Project of ISCAS
The lack of interpretability of existing CNN-based hand detection methods makes it difficult to understand the rationale behind their predictions. In this paper, we propose a novel neural network model, which introduces interpretability into hand detection for the first time. The main improvements include: (1) Detect hands at pixel level to explain what pixels are the basis for its decision and improve transparency of the model. (2) The explainable Highlight Feature Fusion block highlights distinctive features among multiple layers and learns discriminative ones to gain robust performance. (3) We introduce a transparent representation, the rotation map, to learn rotation features instead of complex and non-transparent rotation and derotation layers. (4) Auxiliary supervision accelerates the training process, which saves more than 10 h in our experiments. Experimental results on the VIVA and Oxford hand detection and tracking datasets show competitive accuracy of our method compared with state-of-the-art methods with higher speed. Models and code are available: https://isrc.iscas.ac.cn/gitlab/research/pr2020-phdn. (C) 2020 Elsevier Ltd. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据