TY - GEN
T1 - HYPERGRAPH CONVOLUTIONAL NETWORKS FOR WEAKLY-SUPERVISED SEMANTIC SEGMENTATION
AU - Giraldo, Jhony H.
AU - Scarrica, Vincenzo
AU - Staiano, Antonino
AU - Camastra, Francesco
AU - Bouwmans, Thierry
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022/1/1
Y1 - 2022/1/1
N2 - 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.
AB - 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.
KW - Semantic segmentation
KW - hypergraph convolutional networks
KW - weakly supervised learning
UR - https://www.scopus.com/pages/publications/85146704758
U2 - 10.1109/ICIP46576.2022.9897774
DO - 10.1109/ICIP46576.2022.9897774
M3 - Conference contribution
AN - SCOPUS:85146704758
T3 - Proceedings - International Conference on Image Processing, ICIP
SP - 16
EP - 20
BT - 2022 IEEE International Conference on Image Processing, ICIP 2022 - Proceedings
PB - IEEE Computer Society
T2 - 29th IEEE International Conference on Image Processing, ICIP 2022
Y2 - 16 October 2022 through 19 October 2022
ER -