HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information
Skip to Main content Skip to Navigation

Evaluation of Off-The-Shelf CNNs for the Representation of Natural Scenes with Large Seasonal Variations

Abstract : This paper focuses on the evaluation of deep convolutional neural networks for the analysis of images of natural scenes subjected to large seasonal variation as well as significant changes of lighting conditions. The context is the development of tools for long-term natural environment monitoring with an autonomous mobile robot. We report various experiments conducted on a large dataset consisting of a weekly survey of the shore of a small lake over two years using an autonomous surface vessel. This dataset is used first in a place recognition task framed as a classification problem, then in a pose regression task and finally the internal features learned by the network are evaluated for their representation power. All our results are based on the Caffe library and default network structures where possible.
Document type :
Complete list of metadata

Cited literature [24 references]  Display  Hide  Download

Contributor : Cedric Pradalier Connect in order to contact the contributor
Submitted on : Thursday, February 9, 2017 - 1:21:14 PM
Last modification on : Wednesday, November 3, 2021 - 8:36:09 AM
Long-term archiving on: : Wednesday, May 10, 2017 - 1:34:07 PM


Files produced by the author(s)


Distributed under a Creative Commons Attribution 4.0 International License


  • HAL Id : hal-01448091, version 2


Amandine Gout, Yann Lifchitz, Titouan Cottencin, Quentin Groshens, Jérémy Fix, et al.. Evaluation of Off-The-Shelf CNNs for the Representation of Natural Scenes with Large Seasonal Variations. [Research Report] UMI 2958 GeorgiaTech-CNRS; CentraleSupélec UMI GT-CNRS 2958 Université Paris-Saclay. 2017. ⟨hal-01448091v2⟩



Record views


Files downloads