High-Resolution Semantic Labeling with Convolutional Neural Networks

Emmanuel Maggiori 1 Yuliya Tarabalka 1 Guillaume Charpiat 2 Pierre Alliez 1
1 TITANE - Geometric Modeling of 3D Environments
CRISAM - Inria Sophia Antipolis - Méditerranée
2 TAU - TAckling the Underspecified
LRI - Laboratoire de Recherche en Informatique, UP11 - Université Paris-Sud - Paris 11, Inria Saclay - Ile de France, CNRS - Centre National de la Recherche Scientifique : UMR8623
Abstract : 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.
Document type :
Journal articles
Complete list of metadatas

Cited literature [31 references]  Display  Hide  Download


https://hal.inria.fr/hal-01393279
Contributor : Emmanuel Maggiori <>
Submitted on : Tuesday, March 14, 2017 - 9:57:23 AM
Last modification on : Thursday, February 7, 2019 - 2:26:07 PM
Long-term archiving on : Thursday, June 15, 2017 - 12:52:41 PM

Files

Maggiori_HighResLabeling2016.p...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01393279, version 1
  • ARXIV : 1611.01962

Citation

Emmanuel Maggiori, Yuliya Tarabalka, Guillaume Charpiat, Pierre Alliez. High-Resolution Semantic Labeling with Convolutional Neural Networks. IEEE Transactions on Geoscience and Remote Sensing, Institute of Electrical and Electronics Engineers, 2017. ⟨hal-01393279⟩

Share

Metrics

Record views

1020

Files downloads

928