Back to Search
Start Over
Evidential fully convolutional network for semantic segmentation
- Source :
- Applied Intelligence, volume 51, pages 6376-6399 (2021)
- Publication Year :
- 2021
-
Abstract
- 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.<br />Comment: 34 pages, 21 figures
Details
- Database :
- arXiv
- Journal :
- Applied Intelligence, volume 51, pages 6376-6399 (2021)
- Publication Type :
- Report
- Accession number :
- edsarx.2103.13544
- Document Type :
- Working Paper
- Full Text :
- https://doi.org/10.1007/s10489-021-02327-0