Search Results for author: Gaston Lenczner

Found 5 papers, 4 papers with code

Weakly-supervised continual learning for class-incremental segmentation

1 code implementation4 Jan 2022 Gaston Lenczner, Adrien Chan-Hon-Tong, Nicola Luminari, Bertrand Le Saux

Transfer learning is a powerful way to adapt existing deep learning models to new emerging use-cases in remote sensing.

Continual Learning pseudo label +2

DIAL: Deep Interactive and Active Learning for Semantic Segmentation in Remote Sensing

1 code implementation4 Jan 2022 Gaston Lenczner, Adrien Chan-Hon-Tong, Bertrand Le Saux, Nicola Luminari, Guy Le Besnerais

We propose in this article to build up a collaboration between a deep neural network and a human in the loop to swiftly obtain accurate segmentation maps of remote sensing images.

Active Learning Semantic Segmentation

Demotivate adversarial defense in remote sensing

no code implementations28 May 2021 Adrien Chan-Hon-Tong, Gaston Lenczner, Aurelien Plyer

Convolutional neural networks are currently the state-of-the-art algorithms for many remote sensing applications such as semantic segmentation or object detection.

Adversarial Defense Adversarial Robustness +3

DISIR: Deep Image Segmentation with Interactive Refinement

1 code implementation31 Mar 2020 Gaston Lenczner, Bertrand Le Saux, Nicola Luminari, Adrien Chan Hon Tong, Guy Le Besnerais

Starting from an initial output based on the image only, our network then interactively refines this segmentation map using a concatenation of the image and user annotations.

Image Segmentation Interactive Segmentation +2

Cannot find the paper you are looking for? You can Submit a new open access paper.