Hypergraph Convolutional Networks for Weakly-Supervised Semantic Segmentation - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Hypergraph Convolutional Networks for Weakly-Supervised Semantic Segmentation

Résumé

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 Hy-perGraph 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.

Dates et versions

hal-03841925 , version 1 (07-11-2022)

Identifiants

Citer

Jhony Giraldo, Vincenzo Scarrica, Antonino Staiano, Francesco Camastra, Thierry Bouwmans. Hypergraph Convolutional Networks for Weakly-Supervised Semantic Segmentation. 2022 IEEE International Conference on Image Processing (ICIP), Oct 2022, Bordeaux, France. pp.16-20, ⟨10.1109/ICIP46576.2022.9897774⟩. ⟨hal-03841925⟩
43 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More