1.视频教程:
B站、网易云课堂、腾讯课堂
2.代码地址:
Gitee
Github
3.存储地址:
Google云
百度云:
提取码:
《ExFuse:Enhancing Feature Fusion for Semantic Segmentation》
—待写
作者:Zhenli Zhang,etc
单位:旷视科技
发表会议及时间:ECCV 2018
Submission history
From: Zhenli Zhang [view email]
[v1] Wed, 11 Apr 2018 05:54:31 UTC (1,352 KB)
https://arxiv.org/abs/1804.03821
GCN的延续
- Abstract
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 is 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.
- 背景介绍:现代语义分割框架通常使用特征融合的方式提升性能,但由于高级特征和低级特征之间存在差距,直接融合的效果并不是很好
- 文章思想:在低层特征中引入语义信息,在高层特征中引入细节信息会使后续融合更有效
- 创新点:提出了ExFuse,用来弥补高低层特征之间的差距
- 模型评估:在PASCAL VOC 2012数据集中得到了87.9%的MloU
一 论文导读
二 论文精读
三 代码实现