Jérôme Rony
YOU?
Author Swipe
View article: AttackBench: Evaluating Gradient-based Attacks for Adversarial Examples
AttackBench: Evaluating Gradient-based Attacks for Adversarial Examples Open
While novel gradient-based attacks are continuously proposed to improve the optimization of adversarial examples, each is shown to outperform its predecessors using different experimental setups, implementations, and computational budgets,…
View article: AttackBench: Evaluating Gradient-based Attacks for Adversarial Examples
AttackBench: Evaluating Gradient-based Attacks for Adversarial Examples Open
Adversarial examples are typically optimized with gradient-based attacks. While novel attacks are continuously proposed, each is shown to outperform its predecessors using different experimental setups, hyperparameter settings, and number …
View article: Proximal Splitting Adversarial Attack for Semantic Segmentation
Proximal Splitting Adversarial Attack for Semantic Segmentation Open
International audience
View article: Deep Weakly-Supervised Learning Methods for Classification and Localization in Histology Images: A Survey
Deep Weakly-Supervised Learning Methods for Classification and Localization in Histology Images: A Survey Open
Using state-of-the-art deep learning (DL) models to diagnose cancer from histology data presents several challenges related to the nature and availability of labeled histology images, including image size, stain variations, and label ambig…
View article: Class Adaptive Network Calibration
Class Adaptive Network Calibration Open
Recent studies have revealed that, beyond conventional accuracy, calibration should also be considered for training modern deep neural networks. To address miscalibration during learning, some methods have explored different penalty functi…
View article: Proximal Splitting Adversarial Attacks for Semantic Segmentation
Proximal Splitting Adversarial Attacks for Semantic Segmentation Open
Classification has been the focal point of research on adversarial attacks, but only a few works investigate methods suited to denser prediction tasks, such as semantic segmentation. The methods proposed in these works do not accurately so…
View article: Leveraging Uncertainty for Deep Interpretable Classification and Weakly-Supervised Segmentation of Histology Images
Leveraging Uncertainty for Deep Interpretable Classification and Weakly-Supervised Segmentation of Histology Images Open
Trained using only image class label, deep weakly supervised methods allow image classification and ROI segmentation for interpretability. Despite their success on natural images, they face several challenges over histology data where ROI …
View article: Augmented Lagrangian Adversarial Attacks
Augmented Lagrangian Adversarial Attacks Open
Adversarial attack algorithms are dominated by penalty methods, which are slow in practice, or more efficient distance-customized methods, which are heavily tailored to the properties of the distance considered. We propose a white-box atta…
View article: Mutual-Information Based Few-Shot Classification
Mutual-Information Based Few-Shot Classification Open
We introduce Transductive Infomation Maximization (TIM) for few-shot learning. Our method maximizes the mutual information between the query features and their label predictions for a given few-shot task, in conjunction with a supervision …
View article: Deep Interpretable Classification and Weakly-Supervised Segmentation of Histology Images via Max-Min Uncertainty
Deep Interpretable Classification and Weakly-Supervised Segmentation of Histology Images via Max-Min Uncertainty Open
Weakly-supervised learning (WSL) has recently triggered substantial interest as it mitigates the lack of pixel-wise annotations. Given global image labels, WSL methods yield pixel-level predictions (segmentations), which enable to interpre…
View article: Transductive Information Maximization For Few-Shot Learning
Transductive Information Maximization For Few-Shot Learning Open
We introduce Transductive Infomation Maximization (TIM) for few-shot learning. Our method maximizes the mutual information between the query features and their label predictions for a given few-shot task, in conjunction with a supervision …
View article: Feed-forward weakly supervised deep learning models for breast cancer diagnosis from histological images
Feed-forward weakly supervised deep learning models for breast cancer diagnosis from histological images Open
Breast cancer screening has become one of the top priorities to reduce the number of deaths from breast cancer and treat it as soon as possible. When making a diagnosis for breast cancer, the gold standard is histological image analysis. H…
View article: Deep Weakly-Supervised Learning Methods for Classification and Localization in Histology Images: A Survey
Deep Weakly-Supervised Learning Methods for Classification and Localization in Histology Images: A Survey Open
Using deep learning models to diagnose cancer from histology data presents several challenges. Cancer grading and localization of regions of interest (ROIs) in these images normally relies on both image- and pixel-level labels, the latter …
View article: Universal Adversarial Audio Perturbations
Universal Adversarial Audio Perturbations Open
We demonstrate the existence of universal adversarial perturbations, which can fool a family of audio classification architectures, for both targeted and untargeted attack scenarios. We propose two methods for finding such perturbations. T…
View article: Weakly Supervised Object Localization using Min-Max Entropy: an Interpretable Framework.
Weakly Supervised Object Localization using Min-Max Entropy: an Interpretable Framework. Open
Pointwise localization allows more precise localization and accurate interpretability, compared to bounding box, in applications where objects are highly unstructured such as in medical domain. In this work, we focus on weakly supervised l…
View article: Min-max Entropy for Weakly Supervised Pointwise Localization
Min-max Entropy for Weakly Supervised Pointwise Localization Open
Pointwise localization allows more precise localization and accurate interpretability, compared to bounding box, in applications where objects are highly unstructured such as in medical domain. In this work, we focus on weakly supervised l…
View article: Decoupling Direction and Norm for Efficient Gradient-Based L2 Adversarial Attacks and Defenses
Decoupling Direction and Norm for Efficient Gradient-Based L2 Adversarial Attacks and Defenses Open
Research on adversarial examples in computer vision tasks has shown that small, often imperceptible changes to an image can induce misclassification, which has security implications for a wide range of image processing systems. Considering…