CMGNet: Context-aware middle-layer guidance network for salient object detection
Authors:
- Inam UllahInam Ullah
- Sumaira HussainSHSumaira Hussain
- Kashif ShaheedKSKashif Shaheed
- Wajid AliWAWajid Ali
- Shahid Ali KhanSKShahid Ali Khan
- Yilong YinYYYilong Yin
- Yuling MaYMYuling Ma
Open Access
- 1 January 2024
- journal article
- research article
- Published by Springer Nature in Journal of King Saud University Computer and Information Sciences
- Vol. 36 (1)
Abstract
Salient object detection (SOD) is a critical task in computer vision that involves accurately identifying and segmenting visually significant objects in an image. To address the challenges of gridding issues and feature dilution effects commonly encountered in SOD, we propose a sophisticated context-aware middle-layer guidance network (CMGNet). CMGNet incorporates the context-aware central-layer guidance module (CCGM), which utilizes cost-effective large kernels of depth-wise convolutions with embedded parallel channel attentions and squeeze-and-excitation (SeE) attentions mechanisms. It enables the model to effectively perceive objects of varying scales in complex scenarios. Additionally, the incorporation of the adjacent-to-central-layers paradigm enriches the model’s ability to capture more structural and contextual information. To further enhance performance, we introduce the dual-phase central-layer refinement module (DCRM), which effectively removes the minute blurry residuals in complex scenarios and enhances object segmentation. Moreover, we propose a novel hybrid loss function that handles hard pixels at or near boundaries by incorporating a weighting formula. This hybrid loss function combines binary cross-entropy (BCE), intersection over union (IoU), and consistency-enhanced loss (CEL), resulting in smoother and more precise saliency maps. Extensive evaluations on challenging datasets demonstrate the superiority of our approach over 15 state-of-the-art methods in salient object detection.Keywords
Funding Information
- National Natural Science Foundation of China (62177031)
- Natural Science Foundation of Shandong Province (ZR2021MF044)
This publication has 66 references indexed in Scilit:
- DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- Video Saliency Detection via Spatial-Temporal Fusion and Low-Rank Coherency DiffusionIEEE Transactions on Image Processing, 2017
- Deep Residual Learning for Image Recognition2016
- Stacked Attention Networks for Image Question Answering2016
- DHSNet: Deep Hierarchical Saliency Network for Salient Object Detection2016
- Robust Pre-processing Technique Based on Saliency Detection for Content Based Image Retrieval SystemsProcedia Computer Science, 2016
- Salient Object Detection: A BenchmarkIEEE Transactions on Image Processing, 2015
- Fully convolutional networks for semantic segmentation2015
- A Tutorial on the Cross-Entropy MethodAnnals of Operations Research, 2005
- Computational modelling of visual attentionNature Reviews Neuroscience, 2001