8 papers
Lipschitz bounds for integral kernels
Justin Reverdi, Sixin Zhang, Fabrice Gamboa +1
Feature maps associated with positive definite kernels play a central role in kernel methods and learning theory, where regularity properties such as Lipschitz continuity are close…
Feature Representation Transferring to Lightweight Models via Perception Coherence
Hai-Vy Nguyen, Fabrice Gamboa, Sixin Zhang +3
In this paper, we propose a method for transferring feature representation to lightweight student models from larger teacher models. We mathematically define a new notion called \t…
Convolutional Rectangular Attention Module
Hai-Vy Nguyen, Fabrice Gamboa, Sixin Zhang +3
In this paper, we introduce a novel spatial attention module that can be easily integrated to any convolutional network. This module guides the model to pay attention to the most d…
CNN-based Compressor Mass Flow Estimator in Industrial Aircraft Vapor Cycle System
Justin Reverdi, Sixin Zhang, Saïd Aoues +3
In Vapor Cycle Systems, the mass flow sensor playsa key role for different monitoring and control purposes. However,physical sensors can be inaccurate, heavy, cumbersome, expensive…
Sensitivity Analysis for Active Sampling, with Applications to the Simulation of Analog Circuits
Reda Chhaibi, Fabrice Gamboa, Christophe Oger +3
We propose an active sampling flow, with the use-case of simulating the impact of combined variations on analog circuits. In such a context, given the large number of parameters, i…
Statistical Edge Detection And UDF Learning For Shape Representation
Virgile Foy, Fabrice Gamboa, Reda Chhaibi
In the field of computer vision, the numerical encoding of 3D surfaces is crucial. It is classical to represent surfaces with their Signed Distance Functions (SDFs) or Unsigned Dis…
Training More Robust Classification Model via Discriminative Loss and Gaussian Noise Injection
Hai-Vy Nguyen, Fabrice Gamboa, Sixin Zhang +3
Robustness of deep neural networks to input noise remains a critical challenge, as naive noise injection often degrades accuracy on clean (uncorrupted) data. We propose a novel tra…
Combining Statistical Depth and Fermat Distance for Uncertainty Quantification
Hai-Vy Nguyen, Fabrice Gamboa, Reda Chhaibi +3
We measure the Out-of-domain uncertainty in the prediction of Neural Networks using a statistical notion called ``Lens Depth'' (LD) combined with Fermat Distance, which is able to…