Back to Search Start Over

CAN: Contextual Aggregating Network for Semantic Segmentation

CAN: Contextual Aggregating Network for Semantic Segmentation

Authors :
Huimin Lu
Quan Zhou
Suofei Zhang
Dechun Cong
Xiaofu Wu
Jie Cheng
Weihua Ou
Source :
ICASSP
Publication Year :
2019
Publisher :
IEEE, 2019.

Abstract

Fully convolutional neural networks (FCNs) have shown great success in dense estimation tasks. One key pillar of such progress is mining multi-scale context cues from features in different convolutional layers. This paper introduces contextual aggregating network(CAN), a generic convolutional feature ensembling framework for semantic segmentation. Our framework first captures multi-scale contextual clues by concatenating multi-level feature representation, which carries both coarse semantics and fine details. Then it adaptively integrates stacked features to perform dense pixel estimation. The proposed CAN is trainable end-to-end, and allows us to fully investigate multi-scale context information embedded in images. The experiments show the promising results of our method on PASCAL VOC 2012 and Cityscapes dataset.

Details

Database :
OpenAIRE
Journal :
ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Accession number :
edsair.doi...........aaa6fbf63d4e2f5ff600d2ae6f66e126
Full Text :
https://doi.org/10.1109/icassp.2019.8683673