CAN: Contextual Aggregating Network for Semantic Segmentation
Dechun Cong, Quan Zhou, Jie Cheng, Xiaofu Wu, Suofei Zhang, Weihua Ou, Huimin Lu
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.
BibTeX
@inproceedings{icassp2019_cancontextualagg,
title = {CAN: Contextual Aggregating Network for Semantic Segmentation},
author = {Dechun Cong and Quan Zhou and Jie Cheng and Xiaofu Wu and Suofei Zhang and Weihua Ou and Huimin Lu},
booktitle = {ICASSP 2019},
year = {2019}
}