5 citations · 13 across the 8 of their papers we have counts for
12 papers
Packed-Ensemble Surrogate Models for Fluid Flow Estimation Arround Airfoil Geometries
Anthony Kalaydjian, Anton Balykov, Alexi Semiz +1
Physical based simulations can be very time and computationally demanding tasks. One way of accelerating these processes is by making use of data-driven surrogate models that learn…
Carpet-bombing patch: attacking a deep network without usual requirements
Pol Labarbarie, Adrien Chan-Hon-Tong, Stéphane Herbin +1
Although deep networks have shown vulnerability to evasion attacks, such attacks have usually unrealistic requirements. Recent literature discussed the possibility to remove or not…
DIAL: Deep Interactive and Active Learning for Semantic Segmentation in Remote Sensing
Gaston Lenczner, Adrien Chan-Hon-Tong, Bertrand Le Saux +2
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.…
Weakly-supervised continual learning for class-incremental segmentation
Gaston Lenczner, Adrien Chan-Hon-Tong, Nicola Luminari +1
Transfer learning is a powerful way to adapt existing deep learning models to new emerging use-cases in remote sensing. Starting from a neural network already trained for semantic…
Demotivate adversarial defense in remote sensing
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. However, these a…
Learning-based vs Model-free Adaptive Control of a MAV under Wind Gust
Thomas Chaffre, Julien Moras, Adrien Chan-Hon-Tong +4
Navigation problems under unknown varying conditions are among the most important and well-studied problems in the control field. Classic model-based adaptive control methods can b…
SALAD: Self-Assessment Learning for Action Detection
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.…
Interactive Learning for Semantic Segmentation in Earth Observation
Gaston Lenczner, Adrien Chan-Hon-Tong, Nicola Luminari +2
Dense pixel-wise classification maps output by deep neural networks are of extreme importance for scene understanding. However, these maps are often partially inaccurate due to a v…
Sim-to-Real Transfer with Incremental Environment Complexity for Reinforcement Learning of Depth-Based Robot Navigation
Thomas Chaffre, Julien Moras, Adrien Chan-Hon-Tong +1
Transferring learning-based models to the real world remains one of the hardest problems in model-free control theory. Due to the cost of data collection on a real robot and the li…
ActionSpotter: Deep Reinforcement Learning Framework for Temporal Action Spotting in Videos
Guillaume Vaudaux-Ruth, Adrien Chan-Hon-Tong, Catherine Achard
Summarizing video content is an important task in many applications. This task can be defined as the computation of the ordered list of actions present in a video. Such a list coul…
DISIR: Deep Image Segmentation with Interactive Refinement
Gaston Lenczner, Bertrand Le Saux, Nicola Luminari +2
This paper presents an interactive approach for multi-class segmentation of aerial images. Precisely, it is based on a deep neural network which exploits both RGB images and annota…
The self-concordant perceptron is efficient on a sub-family feasibility instances
Adrien Chan-Hon-Tong
Strict linear feasibility or linear separation is usually tackled using efficient approximation/stochastic algorithms (that may even run in sub-linear times in expectation). Howeve…