Multi Receptive Field Network for Semantic Segmentation

Yuan Jianlong, Deng Zelu, Shu Wang, Zhenbo Luo; The IEEE Winter Conference on Applications of Computer Vision (WACV), 2020, pp. 1894-1903

Abstract


Semantic segmentation is one of the key tasks in computer vision, which is to assign a category label to each pixel in an image. Despite significant progress achieved recently, most existing methods still suffer from two challenging issues: 1) the size of objects and stuff in an image can be very diverse, demanding for incorporating multi-scale features into the fully convolutional networks (FCNs); 2) the pixels close to or at the boundaries of object/stuff are hard to classify due to the intrinsic weakness of convolutional networks. To address the first issue, we propose a new Multi-Receptive Field Module (MRFM), explicitly taking multi-scale features into account. For the second issue, we design an edge-aware loss which is effective in distinguishing the boundaries of object/stuff. With these two designs, our Multi Receptive Field Network achieves new state-of-the-art results on two widely-used semantic segmentation benchmark datasets. Specifically, we achieve a mean IoU of 83.0% on the Cityscapes dataset and 88.4% mean IoU on the pascal VOC2012 dataset.

Related Material


[pdf]
[bibtex]
@InProceedings{Jianlong_2020_WACV,
author = {Jianlong, Yuan and Zelu, Deng and Wang, Shu and Luo, Zhenbo},
title = {Multi Receptive Field Network for Semantic Segmentation},
booktitle = {The IEEE Winter Conference on Applications of Computer Vision (WACV)},
month = {March},
year = {2020}
}