Hypergraph Convolutional Networks for Weakly-Supervised Semantic Segmentation

TL;DR

This paper introduces HyperGraph Convolutional Networks for weakly-supervised semantic segmentation, leveraging hypergraphs constructed from images with sparse annotations to improve segmentation accuracy with less supervision.

Contribution

The paper proposes a novel HyperGraph Convolutional Network architecture that utilizes spatial and k-NN graphs for weakly-supervised semantic segmentation, generating pseudo-labels for training.

Findings

Competitive performance on PASCAL VOC 2012 dataset

Effective use of weak signals like scribbles or clicks

Improved segmentation accuracy with less supervision

Abstract

Semantic segmentation is a fundamental topic in computer vision. Several deep learning methods have been proposed for semantic segmentation with outstanding results. However, these models require a lot of densely annotated images. To address this problem, we propose a new algorithm that uses HyperGraph Convolutional Networks for Weakly-supervised Semantic Segmentation (HyperGCN-WSS). Our algorithm constructs spatial and k-Nearest Neighbor (k-NN) graphs from the images in the dataset to generate the hypergraphs. Then, we train a specialized HyperGraph Convolutional Network (HyperGCN) architecture using some weak signals. The outputs of the HyperGCN are denominated pseudo-labels, which are later used to train a DeepLab model for semantic segmentation. HyperGCN-WSS is evaluated on the PASCAL VOC 2012 dataset for semantic segmentation, using scribbles or clicks as weak signals. Our algorithm shows competitive performance against previous methods.