ExFuse: Enhancing Feature Fusion for Semantic Segmentation

Zhenli Zhang, Xiangyu Zhang, Chao Peng, Xiangyang Xue, Jian Sun; Proceedings of the European Conference on Computer Vision (ECCV), 2018, pp. 269-284


Modern semantic segmentation frameworks usually combine low-level and high-level features from pre-trained backbone convolutional models to boost performance. In this paper, we first point out that a simple fusion of low-level and high-level features could be less effective because of the gap in semantic levels and spatial resolution. We find that introducing semantic information into low-level features and high-resolution details into high-level features are more effective for the later fusion. Based on this observation, we propose a new framework, named ExFuse, to bridge the gap between low-level and high-level features thus significantly improve the segmentation quality by 4.0% in total. Furthermore, we evaluate our approach on the challenging PASCAL VOC 2012 segmentation benchmark and achieve 87.9% mean IoU, which outperforms the previous state-of-the-art results.

Related Material

[pdf] [arXiv]
author = {Zhang, Zhenli and Zhang, Xiangyu and Peng, Chao and Xue, Xiangyang and Sun, Jian},
title = {ExFuse: Enhancing Feature Fusion for Semantic Segmentation},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
month = {September},
year = {2018}