no code implementations • 10 May 2021 • Qinyao Chang, Shiping Zhu
Multi-level features are important for saliency detection.
1 code implementation • CVPR 2021 • Lanyun Zhu, Deyi Ji, Shiping Zhu, Weihao Gan, Wei Wu, Junjie Yan
In this paper, we fully take advantages of the low-level texture features and propose a novel Statistical Texture Learning Network (STLNet) for semantic segmentation.
1 code implementation • 27 Apr 2020 • Xuanyi Liu, Lanyun Zhu, Shiping Zhu, Li Luo
Recent works have achieved great success in improving the performance of multiple computer vision tasks by capturing features with a high channel number utilizing deep neural networks.
no code implementations • 17 Jul 2019 • Shiping Zhu, Lanyun Zhu
However, most of the existing attention modules used in salient object detection are input with the processed feature map itself, which easily leads to the problem of `blind overconfidence'.