1 code implementation • 5 Jul 2022 • Jialun Pei, Tianyang Cheng, Deng-Ping Fan, He Tang, Chuanbo Chen, Luc van Gool
We present OSFormer, the first one-stage transformer framework for camouflaged instance segmentation (CIS).
no code implementations • 11 Dec 2020 • Hua Li, Yuheng Jia, Runmin Cong, Wenhui Wu, Sam Kwong, Chuanbo Chen
Consequently, we devise a spatial regularization and propose a novel convex locality-constrained subspace clustering model that is able to constrain the spatial adjacent pixels with similar attributes to be clustered into a superpixel and generate the content-aware superpixels with more detailed boundaries.
no code implementations • 19 Aug 2020 • Jialun Pei, He Tang, Tianyang Cheng, Chuanbo Chen
To this end, we present a cyclic global context salient instance segmentation network (CGCNet), which is supervised by the combination of salient regions and bounding boxes from the ready-made salient object detection datasets.
no code implementations • 29 Sep 2019 • Jialun Pei, He Tang, Chao Liu, Chuanbo Chen
The experimental results on both salient region detection and salient instance segmentation datasets demonstrate the satisfactory performance of our framework.
no code implementations • 5 Jun 2018 • Jianzhong Sheng, Chuanbo Chen, Chenchen Fu, Chun Jason Xue
Convolution operations dominate the overall execution time of Convolutional Neural Networks (CNNs).