Rethinking Class Activation Maps for Segmentation: Revealing Semantic Information in Shallow Layers by Reducing Noise

no code implementations • 4 Aug 2023 • Hang-Cheng Dong, Yuhao Jiang, Yingyan Huang, Jingxiao Liao, Bingguo Liu, Dong Ye, Guodong Liu

A major limitation to the performance of the class activation maps is the small spatial resolution of the feature maps in the last layer of the convolutional neural network.

Denoising Weakly-supervised Learning +2

CG-fusion CAM: Online segmentation of laser-induced damage on large-aperture optics

no code implementations • 18 Jul 2023 • Yueyue Han, Yingyan Huang, Hangcheng Dong, Fengdong Chen, Fa Zeng, Zhitao Peng, Qihua Zhu, Guodong Liu

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 light interference.

Segmentation Weakly supervised Semantic Segmentation +1