Search Results for author: Adrien Chan-Hon-Tong

Found 8 papers, 3 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

Learning-based vs Model-free Adaptive Control of a MAV under Wind Gust

no code implementations29 Jan 2021 Thomas Chaffre, Julien Moras, Adrien Chan-Hon-Tong, Julien Marzat, Karl Sammut, Gilles Le Chenadec, Benoit Clement

We compare it, in realistic simulations, to a model-free controller that uses the same deep reinforcement learning framework for the control of a micro aerial vehicle under wind gust.


SALAD: Self-Assessment Learning for Action Detection

no code implementations13 Nov 2020 Guillaume Vaudaux-Ruth, Adrien Chan-Hon-Tong, Catherine Achard

Literature on self-assessment in machine learning mainly focuses on the production of well-calibrated algorithms through consensus frameworks i. e. calibration is seen as a problem.

Action Detection Action Localization

ActionSpotter: Deep Reinforcement Learning Framework for Temporal Action Spotting in Videos

no code implementations15 Apr 2020 Guillaume Vaudaux-Ruth, Adrien Chan-Hon-Tong, Catherine Achard

In this work, we propose to directly compute this ordered list by sparsely browsing the video and selecting one frame per action instance, task known as action spotting in literature.

Action Detection Action Spotting +1

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