Local to Global Feature Learning for Salient Object Detection

Xuelu Feng, Sanping Zhou, Zixin Zhu, Le Wang, Gang Hua

Abstract: Highlights•We present a novel Local to Global Feature (L2GF) Learning network for salient object detection.•We design a L-Net and a G-Net to learn local and global contexts from the low-level and high-level features, respectively.•For L-Net, it extracts coarse local context in the first stage and models the fine-grained details in the second stage.•For G-Net, the idea of modeling is from the perspective of sequence to sequence prediction to obtain global context.•We build a simple yet effective fusion branch (F-Net) to aggregate the local and global contexts for the final filtering.