1 citations · 1 across the 3 of their papers we have counts for
3 papers
cs.CV2023★ 1 cited
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…
cs.CV2023
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…
cs.LG2021
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…