Pixels, Regions, and Objects: Multiple Enhancement for Salient Object Detection
Authors:
- 1 June 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 10031-10040
Abstract
Salient object detection (SOD) aims to mimic the human visual system (HVS) and cognition mechanisms to identify and segment salient objects. However, due to the complexity of these mechanisms, current methods are not perfect. Accuracy and robustness need to be further improved, particularly in complex scenes with multiple objects and background clutter. To address this issue, we propose a novel approach called Multiple Enhancement Network (MENet) that adopts the boundary sensibility, content integrity, iterative refinement, and frequency decomposition mechanisms of HVS. A multi-level hybrid loss is firstly designed to guide the network to learn pixel-level, region-level, and object-level features. A flexible multiscale feature enhancement module (ME-Module) is then designed to gradually aggregate and refine global or detailed features by changing the size order of the input feature sequence. An iterative training strategy is used to enhance boundary features and adaptive features in the dual-branch decoder of MENet. Comprehensive evaluations on six challenging benchmark datasets show that MENet achieves state-of-the-art results. Both the codes and results are publicly available at https://github.com/yiwangtz/MENet.Keywords
Funding Information
- National Natural Science Foundation of China (61976037,U22B2052)
This publication has 46 references indexed in Scilit:
- ImageNet classification with deep convolutional neural networksCommunications of the ACM, 2017
- Optimizing Intersection-Over-Union in Deep Neural Networks for Image Segmentation2016
- Deep Residual Learning for Image Recognition2016
- Fully convolutional networks for semantic segmentation2015
- Hierarchical Saliency Detection2013
- Saliency Detection via Graph-Based Manifold Ranking2013
- Saliency filters: Contrast based filtering for salient region detection2012
- Stochastic Gradient Descent Tricks2012
- A Tutorial on the Cross-Entropy MethodAnnals of Operations Research, 2005
- Neurophysiological interpretation of human visual reaction times: effect of contrast, spatial frequency and luminanceNeuropsychologia, 2000