Affinity Attention Graph Neural Network for Weakly Supervised Semantic Segmentation

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\%, test: 75.2\%). 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.

arXiv commentAccepted by IEEE Transactions on Pattern Analysis and Machine Intelligence (TAPMI 2021)

References in corpus (11)

• Adam: A Method for Stochastic Optimization
• Rethinking Atrous Convolution for Semantic Image Segmentation
• Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
• Res2Net: A New Multi-scale Backbone Architecture
• Fully Convolutional Networks for Semantic Segmentation
• STC: A Simple to Complex Framework for Weakly-supervised Semantic Segmentation
• Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation
• Attention-based Graph Neural Network for Semi-supervised Learning
• Learning random-walk label propagation for weakly-supervised semantic segmentation
• Learnable Tree Filter for Structure-preserving Feature Transform
• Improving Semantic Segmentation via Dilated Affinity

Cited by in corpus (11)

• Medical Image Segmentation Using Deep Learning: A Survey
• Self-supervised Image-specific Prototype Exploration for Weakly Supervised Semantic Segmentation
• Gaussian Dynamic Convolution for Efficient Single-Image Segmentation
• Adaptive Patch Contrast for Weakly Supervised Semantic Segmentation
• Graph Foundation Models: Concepts, Opportunities and Challenges
• Scribble Hides Class: Promoting Scribble-Based Weakly-Supervised Semantic Segmentation with Its Class Label
• Dynamic Feature Regularized Loss for Weakly Supervised Semantic Segmentation
• Hypergraph Convolutional Network based Weakly Supervised Point Cloud Semantic Segmentation with Scene-Level Annotations
• Contrastive Proposal Extension with LSTM Network for Weakly Supervised Object Detection
• Multi-Level Label Correction by Distilling Proximate Patterns for Semi-supervised Semantic Segmentation
• Maximize the Exploration of Congeneric Semantics for Weakly Supervised Semantic Segmentation