Title
Spatial context-aware network for salient object detection
Document Type
Article
Publication Date
6-1-2021
Abstract
Salient Object Detection (SOD) is a fundamental problem in the field of computer vision. This paper presents a novel Spatial Context-Aware Network (SCA-Net) for SOD in images. Compared with other recent deep learning based SOD algorithms, SCA-Net can more effectively aggregate multi-level deep features. A Long-Path Context Module (LPCM) is employed to grant better discrimination ability to feature maps that incorporate coarse global information. Consequently, a more accurate initial saliency map can be obtained to facilitate subsequent predictions. SCA-Net also adopts a Short-Path Context Module (SPCM) to progressively enforce the interaction between local contextual cues and global features. Extensive experiments on five large-scale benchmarks demonstrate that SCA-Net achieves favorable performance against very recent state-of-the-art algorithms.
Publication Source (Journal or Book title)
Pattern Recognition
Recommended Citation
Kong, Y., Feng, M., Li, X., Lu, H., Liu, X., & Yin, B. (2021). Spatial context-aware network for salient object detection. Pattern Recognition, 114 https://doi.org/10.1016/j.patcog.2021.107867