2 Hits in 4.6 sec

SAC-Net: Spatial Attenuation Context for Salient Object Detection [article]

Xiaowei Hu, Chi-Wing Fu, Lei Zhu, Tianyu Wang, Pheng-Ann Heng
2020 arXiv   pre-print
By further embedding the module to process individual layers in a deep network, namely SAC-Net, we can train the network end-to-end and optimize the context features for detecting salient objects.  ...  This paper presents a new deep neural network design for salient object detection by maximizing the integration of local and global image context within, around, and beyond the salient objects.  ...  Moreover, we compare the time performance of our SAC-Net with other methods for salient object detection.  ... 
arXiv:1903.10152v3 fatcat:rfd5v5basjgl7fqs7rqoupt7fy

Boundary-Aware Segmentation Network for Mobile and Web Applications [article]

Xuebin Qin and Deng-Ping Fan and Chenyang Huang and Cyril Diagne and Zichen Zhang and Adrià Cabeza Sant'Anna and Albert Suàrez and Martin Jagersand and Ling Shao
2021 arXiv   pre-print
CUT, which is a web-based tool for automatic object background removal.  ...  We evaluate our BASNet on two reverse tasks including salient object segmentation, camouflaged object segmentation, showing that it achieves very competitive performance with sharp segmentation boundaries  ...  (SAC-Net) [38] developed similar strategies to [68] to capture spatial attenuation context for image segmentation. Zhang et al.  ... 
arXiv:2101.04704v2 fatcat:irni2rl3bbbrbjjuk3s6bz32fe