Affinity attention graph neural network for weakly supervised semantic segmentation

Bingfeng Zhang, Jimin Xiao, Jianbo Jiao, Yunchao Wei, Yao Zhao

Research output: Contribution to journalArticlepeer-review


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 (A2GNN). 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 A2GNN, 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 A2GNN, 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 or comparable performances on Pascal VOC 2012 datasets (val: 76.5%, test: 75.2%).
Original languageEnglish
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Early online date25 May 2021
Publication statusE-pub ahead of print - 25 May 2021


  • cs.CV


Dive into the research topics of 'Affinity attention graph neural network for weakly supervised semantic segmentation'. Together they form a unique fingerprint.

Cite this