Florent Chiaroni
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Florent Chiaroni has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Frederic Dufaux
Université Paris-Saclay, CNRS, CentraleSupélec
2 shared publications - Ghazaleh Khodabandelou
Department of new uses (MOB05) Artificial Intelligence team VEDECOM Institute 23 bis Allee des Marronniers 78000 Versailles France
2 shared publications Mohamed-Cherif Rahal
Department of delegated driving (VEH08) Perception team VEDECOM Institute 23 bis Allee des Marronniers 78000 Versailles France
2 shared publications- Nicolas Hueber
Optoelectronics and Systems, University of Haute Alsace (UHA), Mulhouse, France
2 shared publications Fredericdu Aux
CNRS-CentraleSupelec-Univ Paris-Sud-Univ Paris-Saclay 3 rue Joliot Curie L2S 91190 Gif-sur-Yvette France
1 shared publicationMohamed -Cheri F Rahal
Department of delegated driving (VEH08) Perception team VEDECOM Institute 23 bis Allee des Marronniers 78000 Versailles France
1 shared publication
Latest Publications
- Open Access
Generating Relevant Counter-Examples from a Positive Unlabeled Dataset for Image Classification
With surge of available but unlabeled data, Positive Unlabeled (PU) learning is becoming a thriving challenge. This work deals with this demanding task for which recent GAN-based PU approaches have demonstrated promising results. Generative adversarial Networks (GANs) are not hampered by deterministic bias or need for specific dimensionality. However, existing GAN-based PU approaches also present some drawbacks such as sensitive dependence to prior knowledge, a cumbersome architecture or first-stage overfitting. To settle these issues, we propose to incorporate a biased PU risk within the standard GAN discriminator loss function. In this manner, the discriminator is constrained to request the generator to converge towards the unlabeled samples distribution while diverging from the positive samples distribution. This enables the proposed model, referred to as D-GAN, to exclusively learn the counter-examples distribution without prior knowledge. Experiments demonstrate that our approach outperforms state-of-the-art PU methods without prior by overcoming their issues.
Open AccessGenerating Relevant Counter-Examples from a Positive Unlabeled Dataset for Image Classification
With surge of available but unlabeled data, Positive Unlabeled (PU) learning is becoming a thriving challenge. This work deals with this demanding task for which recent GAN-based PU approaches have demonstrated promising results. Generative adversarial Networks (GANs) are not hampered by deterministic bias or need for specific dimensionality. However, existing GAN-based PU approaches also present some drawbacks such as sensitive dependence to prior knowledge, a cumbersome architecture or first-stage overfitting. To settle these issues, we propose to incorporate a biased PU risk within the standard GAN discriminator loss function. In this manner, the discriminator is constrained to request the generator to converge towards the unlabeled samples distribution while diverging from the positive samples distribution. This enables the proposed model, referred to as D-GAN, to exclusively learn the counter-examples distribution without prior knowledge. Experiments demonstrate that our approach outperforms state-of-the-art PU methods without prior by overcoming their issues.
- Open Access
Generating Relevant Counter-Examples from a Positive Unlabeled Dataset for Image Classification
With surge of available but unlabeled data, Positive Unlabeled (PU) learning is becoming a thriving challenge. This work deals with this demanding task for which recent GAN-based PU approaches have demonstrated promising results. Generative adversarial Networks (GANs) are not hampered by deterministic bias or need for specific dimensionality. However, existing GAN-based PU approaches also present some drawbacks such as sensitive dependence to prior knowledge, a cumbersome architecture or first-stage overfitting. To settle these issues, we propose to incorporate a biased PU risk within the standard GAN discriminator loss function. In this manner, the discriminator is constrained to request the generator to converge towards the unlabeled samples distribution while diverging from the positive samples distribution. This enables the proposed model, referred to as D-GAN, to exclusively learn the counter-examples distribution without prior knowledge. Experiments demonstrate that our approach outperforms state-of-the-art PU methods without prior by overcoming their issues.
Open AccessGenerating Relevant Counter-Examples from a Positive Unlabeled Dataset for Image Classification
With surge of available but unlabeled data, Positive Unlabeled (PU) learning is becoming a thriving challenge. This work deals with this demanding task for which recent GAN-based PU approaches have demonstrated promising results. Generative adversarial Networks (GANs) are not hampered by deterministic bias or need for specific dimensionality. However, existing GAN-based PU approaches also present some drawbacks such as sensitive dependence to prior knowledge, a cumbersome architecture or first-stage overfitting. To settle these issues, we propose to incorporate a biased PU risk within the standard GAN discriminator loss function. In this manner, the discriminator is constrained to request the generator to converge towards the unlabeled samples distribution while diverging from the positive samples distribution. This enables the proposed model, referred to as D-GAN, to exclusively learn the counter-examples distribution without prior knowledge. Experiments demonstrate that our approach outperforms state-of-the-art PU methods without prior by overcoming their issues.