1 code implementation • 26 Oct 2022 • Junliang Chen, Xiaodong Zhao, Cheng Luo, Linlin Shen
Recent mainstream weakly supervised semantic segmentation (WSSS) approaches are mainly based on Class Activation Map (CAM) generated by a CNN (Convolutional Neural Network) based image classifier.
Weakly supervised Semantic Segmentation Weakly-Supervised Semantic Segmentation
no code implementations • 22 Oct 2022 • Junliang Chen, Xiaodong Zhao, Minmin Liu, Linlin Shen
Recent mainstream weakly-supervised semantic segmentation (WSSS) approaches mainly relies on image-level classification learning, which has limited representation capacity.
no code implementations • 7 Aug 2022 • Minmin Liu, Xuechen Li, Xiangbo Gao, Junliang Chen, Linlin Shen, Huisi Wu
Due to the difficulty of cancer samples collection and annotation, cervical cancer datasets usually exhibit a long-tailed data distribution.
no code implementations • 16 Jun 2022 • Junliang Chen, Xiaodong Zhao, Linlin Shen
For most of the single-stage object detectors, replacing the traditional convolutions with MSConvs in the detection head can bring more than 2. 5\% improvement in AP (on COCO 2017 dataset), with only 3\% increase of FLOPs.
no code implementations • 16 Jun 2022 • Junliang Chen, Weizeng Lu, Linlin Shen
When integrated with SMSL, two-stage detectors can get around 1. 0\% improvement in AP.
2 code implementations • 25 Mar 2022 • Jinheng Xie, Jianfeng Xiang, Junliang Chen, Xianxu Hou, Xiaodong Zhao, Linlin Shen
While class activation map (CAM) generated by image classification network has been widely used for weakly supervised object localization (WSOL) and semantic segmentation (WSSS), such classifiers usually focus on discriminative object regions.
1 code implementation • CVPR 2022 • Jinheng Xie, Jianfeng Xiang, Junliang Chen, Xianxu Hou, Xiaodong Zhao, Linlin Shen
While class activation map (CAM) generated by image classification network has been widely used for weakly supervised object localization (WSOL) and semantic segmentation (WSSS), such classifiers usually focus on discriminative object regions.