1 code implementation • 25 Apr 2024 • Aimi Okabayashi, Nicolas Audebert, Simon Donike, Charlotte Pelletier
Satellite imaging generally presents a trade-off between the frequency of acquisitions and the spatial resolution of the images.
no code implementations • 19 Apr 2024 • Georges Le Bellier, Nicolas Audebert
In this work, we show that the reconstruction error of diffusion models can effectively serve as unsupervised out-of-distribution detectors for remote sensing images, using them as a plausibility score.
1 code implementation • 26 Oct 2023 • Perla Doubinsky, Nicolas Audebert, Michel Crucianu, Hervé Le Borgne
This requires to generate images that correspond to a given input number of objects.
Ranked #3 on Object Counting on FSC147 (using extra training data)
1 code implementation • 15 Sep 2023 • Elias Ramzi, Nicolas Audebert, Clément Rambour, André Araujo, Xavier Bitot, Nicolas Thome
It provides an upperbound for rank losses and ensures robust training.
no code implementations • 22 Mar 2023 • Perla Doubinsky, Nicolas Audebert, Michel Crucianu, Hervé Le Borgne
The latent space of GANs contains rich semantics reflecting the training data.
1 code implementation • 5 Jul 2022 • Elias Ramzi, Nicolas Audebert, Nicolas Thome, Clément Rambour, Xavier Bitot
Image Retrieval is commonly evaluated with Average Precision (AP) or Recall@k. Yet, those metrics, are limited to binary labels and do not take into account errors' severity.
Ranked #1 on Metric Learning on DyML-Animal
no code implementations • 3 Feb 2022 • Xinying Cheng, Rafik Zayani, Marin Ferecatu, Nicolas Audebert
Specifically, we aim to design the PA-aware precoder and the receive decoder by leveraging the concept of autoprecoder, whereas the end-to-end massive multiuser (MU)-MIMO downlink is designed using a deep neural network (NN).
1 code implementation • 28 Oct 2021 • Perla Doubinsky, Nicolas Audebert, Michel Crucianu, Hervé Le Borgne
We propose to address disentanglement by subsampling the generated data to remove over-represented co-occuring attributes thus balancing the semantics of the dataset before training the classifiers.
1 code implementation • NeurIPS 2021 • Elias Ramzi, Nicolas Thome, Clément Rambour, Nicolas Audebert, Xavier Bitot
In image retrieval, standard evaluation metrics rely on score ranking, e. g. average precision (AP).
Ranked #2 on Image Retrieval on CUB-200-2011
no code implementations • 26 Aug 2021 • Chen Dang, Hicham Randrianarivo, Raphaël Fournier-S'niehotta, Nicolas Audebert
Web Image Context Extraction (WICE) consists in obtaining the textual information describing an image using the content of the surrounding webpage.
no code implementations • 15 Oct 2020 • Javiera Castillo-Navarro, Bertrand Le Saux, Alexandre Boulch, Nicolas Audebert, Sébastien Lefèvre
The development of semi-supervised learning techniques is essential to enhance the generalization capacities of machine learning algorithms.
no code implementations • 4 Sep 2019 • Nicolas Audebert, Alexandre Boulch, Bertrand Le Saux, Sébastien Lefèvre
This work introduces a new semantic segmentation regularization based on the regression of a distance transform.
3 code implementations • 15 Jul 2019 • Nicolas Audebert, Catherine Herold, Kuider Slimani, Cédric Vidal
Classification of document images is a critical step for archival of old manuscripts, online subscription and administrative procedures.
1 code implementation • IEEE Geoscience and Remote Sensing Magazine 2019 • Nicolas Audebert, Bertrand Saux, Sébastien Lefèvre
1 This article is intended for both data scientists with interest in hyperspectral data and remote sensing experts eager to apply deep learning techniques to their own dataset.
Ranked #14 on Hyperspectral Image Classification on Pavia University (Overall Accuracy metric)
no code implementations • 7 Jun 2018 • Nicolas Audebert, Bertrand Le Saux, Sébastien Lefèvre
This work addresses the scarcity of annotated hyperspectral data required to train deep neural networks.
1 code implementation • 23 Nov 2017 • Nicolas Audebert, Bertrand Le Saux, Sébastien Lefèvre
In this work, we investigate various methods to deal with semantic labeling of very high resolution multi-modal remote sensing data.
no code implementations • 17 May 2017 • Nicolas Audebert, Bertrand Le Saux, Sébastien Lefèvre
In this work, we investigate the use of OpenStreetMap data for semantic labeling of Earth Observation images.
no code implementations • 20 Jan 2017 • Nicolas Audebert, Bertrand Le Saux, Sébastien Lefèvre
We introduce residual correction as a way to learn how to fuse predictions coming out of a dual stream architecture.
no code implementations • 22 Sep 2016 • Nicolas Audebert, Bertrand Le Saux, Sébastien Lefèvre
In this work, we show how to use such deep networks to detect, segment and classify different varieties of wheeled vehicles in aerial images from the ISPRS Potsdam dataset.
no code implementations • 22 Sep 2016 • Nicolas Audebert, Bertrand Le Saux, Sébastien Lefèvre
In this paper, we investigate the impact of segmentation algorithms as a preprocessing step for classification of remote sensing images in a deep learning framework.
no code implementations • 22 Sep 2016 • Nicolas Audebert, Bertrand Le Saux, Sébastien Lefèvre
This work investigates the use of deep fully convolutional neural networks (DFCNN) for pixel-wise scene labeling of Earth Observation images.