Journal
PATTERN RECOGNITION
Volume 105, Issue -, Pages -Publisher
ELSEVIER SCI LTD
DOI: 10.1016/j.patcog.2020.107202
Keywords
Interpretability; Hand detection; Pixel level; Explainable representation; Rotation map
Funding
- 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
Ask authors/readers for more resources
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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available