On Auxiliary Losses for Semi-Supervised Semantic Segmentation - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

On Auxiliary Losses for Semi-Supervised Semantic Segmentation

Résumé

The development of semi-supervised learning methods is essential to Earth Observation applications. Indeed, labeled remote sensing data are scarce and likely insufficient to train fully supervised models with good generalization capacities. Conversely, raw data are abundant and therefore it is crucial to leverage unlabeled inputs to build better deep learning models. This work addresses the problem of semisupervised semantic segmentation from a multi-task learning perspective. In this context, we explore several auxiliary tasks (reconstruction, unsupervised segmentation or self-supervision), and corresponding unsupervised losses, to perform along with semantic segmentation. Our experiments show the potential of semi-supervised learning approaches in a lifelike scenario, outperforming a classical supervised setting.
Fichier principal
Vignette du fichier
DTIS21087.1618479478.pdf (1.85 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03206301 , version 1 (23-04-2021)

Identifiants

  • HAL Id : hal-03206301 , version 1

Citer

Javiera Castillo-Navarro, Bertrand Le Saux, Alexandre Boulch, Sébastien Lefèvre. On Auxiliary Losses for Semi-Supervised Semantic Segmentation. ECML PKDD 2020: European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, Sep 2020, GHENT, Belgium. ⟨hal-03206301⟩
151 Consultations
220 Téléchargements

Partager

Gmail Facebook X LinkedIn More