期刊
APPLIED INTELLIGENCE
卷 51, 期 9, 页码 6376-6399出版社
SPRINGER
DOI: 10.1007/s10489-021-02327-0
关键词
Evidence theory; Belief function; Fully convolutional network; Decision analysis; Semantic segmentation
资金
- China Scholarship Council
- Labex MS2T [ANR-11-IDEX-0004-02]
The proposed hybrid architecture combines a fully convolutional network with a Dempster-Shafer layer for image semantic segmentation. Through an end-to-end learning strategy and experiments on three databases, the combination improves the accuracy and calibration of semantic segmentation by assigning confusing pixels to multi-class sets.
We propose a hybrid architecture composed of a fully convolutional network (FCN) and a Dempster-Shafer layer for image semantic segmentation. In the so-called evidential FCN (E-FCN), an encoder-decoder architecture first extracts pixel-wise feature maps from an input image. A Dempster-Shafer layer then computes mass functions at each pixel location based on distances to prototypes. Finally, a utility layer performs semantic segmentation from mass functions and allows for imprecise classification of ambiguous pixels and outliers. We propose an end-to-end learning strategy for jointly updating the network parameters, which can make use of soft (imprecise) labels. Experiments using three databases (Pascal VOC 2011, MIT-scene Parsing and SIFT Flow) show that the proposed combination improves the accuracy and calibration of semantic segmentation by assigning confusing pixels to multi-class sets.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据