Skip to Main content Skip to Navigation
Conference papers

Semantic Segmentation via Multi-task, Multi-domain Learning

Abstract : We present an approach that leverages multiple datasets possibly annotated using different classes to improve the semantic segmentation accuracy on each individual dataset. We propose a new selective loss function that can be integrated into deep networks to exploit training data coming from multiple datasets with possibly different tasks (e.g., different label-sets). We show how the gradient-reversal approach for domain adaptation can be used in this setup. Thorought experiments on semantic segmentation applications show the relevance of our approach.
Complete list of metadata

Cited literature [26 references]  Display  Hide  Download
Contributor : Damien Fourure Connect in order to contact the contributor
Submitted on : Thursday, October 6, 2016 - 10:18:33 AM
Last modification on : Sunday, June 26, 2022 - 12:06:13 PM
Long-term archiving on: : Saturday, January 7, 2017 - 1:01:06 PM


Files produced by the author(s)


  • HAL Id : hal-01376998, version 1


Damien Fourure, Rémi Emonet, Elisa Fromont, Damien Muselet, Alain Trémeau, et al.. Semantic Segmentation via Multi-task, Multi-domain Learning. S+SSPR 2016 The joint IAPR International Workshops on Structural and Syntactic Pattern Recognition (SSPR 2016) and Statistical Techniques in Pattern Recognition (SPR 2016) , Nov 2016, Merida, Mexico. ⟨hal-01376998⟩



Record views


Files downloads