High-Resolution Semantic Labeling with Convolutional Neural Networks - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Article Dans Une Revue IEEE Transactions on Geoscience and Remote Sensing Année : 2017

High-Resolution Semantic Labeling with Convolutional Neural Networks

Résumé

Convolutional neural networks (CNNs) have received increasing attention over the last few years. They were initially conceived for image categorization, i.e., the problem of assigning a semantic label to an entire input image. In this paper we address the problem of dense semantic labeling, which consists in assigning a semantic label to every pixel in an image. Since this requires a high spatial accuracy to determine where labels are assigned, categorization CNNs, intended to be highly robust to local deformations, are not directly applicable. By adapting categorization networks, many semantic labeling CNNs have been recently proposed. Our first contribution is an in-depth analysis of these architectures. We establish the desired properties of an ideal semantic labeling CNN, and assess how those methods stand with regard to these properties. We observe that even though they provide competitive results, these CNNs often underexploit properties of semantic labeling that could lead to more effective and efficient architectures. Out of these observations, we then derive a CNN framework specifically adapted to the semantic labeling problem. In addition to learning features at different resolutions, it learns how to combine these features. By integrating local and global information in an efficient and flexible manner, it outperforms previous techniques. We evaluate the proposed framework and compare it with state-of-the-art architectures on public benchmarks of high-resolution aerial image labeling.
Fichier principal
Vignette du fichier
Maggiori_HighResLabeling2016.pdf (6.42 Mo) Télécharger le fichier
Vignette du fichier
thumbnail.jpg (9.8 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Format : Figure, Image
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01393279 , version 1 (14-03-2017)

Identifiants

Citer

Emmanuel Maggiori, Yuliya Tarabalka, Guillaume Charpiat, Pierre Alliez. High-Resolution Semantic Labeling with Convolutional Neural Networks. IEEE Transactions on Geoscience and Remote Sensing, 2017. ⟨hal-01393279⟩
623 Consultations
609 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More