Paper Info
Title
Weakly Supervised Semantic Segmentation By Iteratively Refining Optimal Segmentation With Deep Cues Guidance
Abstract
Weakly supervised semantic segmentation under image-level label supervision has undergone impressive improvements over the past years. These approaches can significantly reduce human annotation efforts, although they remain inferior to fully supervised procedures. In this paper, we propose a novel framework that iteratively refines pixel-level annotations and optimizes segmentation network. We first produce initial deep cues using the combination of activation maps and a saliency map. To produce high-quality pixel-level annotations, a graphical model is constructed over optimal segmentation of high-quality region hierarchies to propagate information from deep cues to unmarked regions. In the training process, the initial pixel-level annotations are used as supervision to train the segmentation network and to predict segmentation masks. To correct inaccurate labels of segmentation masks, we use these segmentation masks with the graphical model to produce accurate pixel-level annotations and use them as supervision to retrain the segmentation network. Experimental results show that the proposed method can significantly outperform the weakly-supervised semantic segmentation methods using static labels. The proposed method has state-of-the-art performance, which are 66.7% mIoU score on PASCAL VOC 2012 test set and 27.0% mIoU score on MS COCO validation set.
Year
DOI
Venue
2021
10.1007/s00521-020-05669-x
NEURAL COMPUTING & APPLICATIONS
Keywords
DocType
Volume
Deep convolutional neural networks, Graphical model, Hierarchical image segmentation, Semantic segmentation, Weakly supervised
Journal
33
Issue
ISSN
Citations 
15
0941-0643
1
PageRank 
References 
Authors
0.35
0
7
Name
Order
Citations
PageRank
Zaid Al‐Huda111.70
Bo Peng2102.93
Yan Yang332.40
Riyadh Nazar Ali Algburi411.37
Muqeet Ahmad510.35
Faisal Khurshid643.07
Khaled Moghalles711.03