1 citations · 1 across the 4 of their papers we have counts for
4 papers
Rethinking Class Activation Maps for Segmentation: Revealing Semantic Information in Shallow Layers by Reducing Noise
Hang-Cheng Dong, Yuhao Jiang, Yingyan Huang +4
Class activation maps are widely used for explaining deep neural networks. Due to its ability to highlight regions of interest, it has evolved in recent years as a key step in weak…
CG-fusion CAM: Online segmentation of laser-induced damage on large-aperture optics
Yueyue Han, Yingyan Huang, Hangcheng Dong +5
Online segmentation of laser-induced damage on large-aperture optics in high-power laser facilities is challenged by complicated damage morphology, uneven illumination and stray li…
Training Neural Networks for Solving 1-D Optimal Piecewise Linear Approximation
Hangcheng Dong, Jingxiao Liao, Yan Wang +4
Recently, the interpretability of deep learning has attracted a lot of attention. A plethora of methods have attempted to explain neural networks by feature visualization, saliency…
How to Explain Neural Networks: an Approximation Perspective
Hangcheng Dong, Bingguo Liu, Fengdong Chen +2
The lack of interpretability has hindered the large-scale adoption of AI technologies. However, the fundamental idea of interpretability, as well as how to put it into practice, re…