Evidential fully convolutional network for semantic segmentation - Archive ouverte HAL Access content directly
Journal Articles Applied Intelligence Year : 2021

Evidential fully convolutional network for semantic segmentation

(1) , (1) , (1, 2)
1
2

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.
Fichier principal
Vignette du fichier
EFCN_revised.pdf (4.89 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03511108 , version 1 (04-01-2022)

Identifiers

Cite

Zheng Tong, Philippe Xu, Thierry Denoeux. Evidential fully convolutional network for semantic segmentation. Applied Intelligence, 2021, 51 (9), pp.6376-6399. ⟨10.1007/s10489-021-02327-0⟩. ⟨hal-03511108⟩
12 View
15 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More