Spatial context-aware network for salient object detection

Yuqiu Kong

doi:10.1016/j.patcog.2021.107867

Return

Spatial context-aware network for salient object detection

2021-06-01

PRE

DOI：10.1016/j.patcog.2021.107867

Original

Original request for help

Save

Abstract

En 中文

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 fea-ture 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. Ex-tensive experiments on five large-scale benchmarks demonstrate that SCA-Net achieves favorable perfor-mance against very recent state-of-the-art algorithms. (c) 2021 Elsevier Ltd. All rights reserved.

Keywords:

Salient object detection

Context-aware methods

Deep learning

AI Summary

Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.