Semantic Segmentation via Multi-task, Multi-domain Learning
Résumé
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.
Fichier principal
Semantic_Segmentation_via_Multi-task_Multi-domain_Learning.pdf (697.49 Ko)
Télécharger le fichier
| Origine | Fichiers produits par l'(les) auteur(s) |
|---|
Loading...