« Previous AbstractElectrochemical oxidation of gaseous benzene on a Sb-SnO(2)/foam Ti nano-coating electrode in all-solid cell    Next AbstractEffects of three indigenous non-Saccharomyces yeasts and their pairwise combinations in co-fermentation with Saccharomyces cerevisiae on volatile compounds of Petit Manseng wines »

IEEE Trans Pattern Anal Mach Intell

Title:		Affinity Attention Graph Neural Network for Weakly Supervised Semantic Segmentation
Author(s):		Zhang B; Xiao J; Jiao J; Wei Y; Zhao Y;
Address:
Journal Title:		IEEE Trans Pattern Anal Mach Intell
Year:		2022
Volume:		20221004
Issue:		11
Page Number:		8082 - 8096
DOI:		10.1109/TPAMI.2021.3083269
ISSN/ISBN:		1939-3539 (Electronic) 0098-5589 (Linking)
Abstract:		"Weakly supervised semantic segmentation is receiving great attention due to its low human annotation cost. In this paper, we aim to tackle bounding box supervised semantic segmentation, i.e., training accurate semantic segmentation models using bounding box annotations as supervision. To this end, we propose affinity attention graph neural network ( A(2)GNN). Following previous practices, we first generate pseudo semantic-aware seeds, which are then formed into semantic graphs based on our newly proposed affinity Convolutional Neural Network (CNN). Then the built graphs are input to our A(2)GNN, in which an affinity attention layer is designed to acquire the short- and long- distance information from soft graph edges to accurately propagate semantic labels from the confident seeds to the unlabeled pixels. However, to guarantee the precision of the seeds, we only adopt a limited number of confident pixel seed labels for A(2)GNN, which may lead to insufficient supervision for training. To alleviate this issue, we further introduce a new loss function and a consistency-checking mechanism to leverage the bounding box constraint, so that more reliable guidance can be included for the model optimization. Experiments show that our approach achieves new state-of-the-art performances on Pascal VOC 2012 datasets (val: 76.5 percent, test: 75.2 percent). More importantly, our approach can be readily applied to bounding box supervised instance segmentation task or other weakly supervised semantic segmentation tasks, with state-of-the-art or comparable performance among almot all weakly supervised tasks on PASCAL VOC or COCO dataset. Our source code will be available at https://github.com/zbf1991/A2GNN"
Keywords:		"Algorithms Attention Humans Image Processing, Computer-Assisted Neural Networks, Computer Semantics *Supervised Machine Learning *Volatile Organic Compounds;"
Notes:		"MedlineZhang, Bingfeng Xiao, Jimin Jiao, Jianbo Wei, Yunchao Zhao, Yao eng Research Support, Non-U.S. Gov't 2021/05/26 IEEE Trans Pattern Anal Mach Intell. 2022 Nov; 44(11):8082-8096. doi: 10.1109/TPAMI.2021.3083269. Epub 2022 Oct 4"