79 citations · 234 across the 13 of their papers we have counts for
14 papers
AttackBench: Evaluating Gradient-based Attacks for Adversarial Examples
Antonio Emanuele Cinà, Jérôme Rony, Maura Pintor +5
Adversarial examples are typically optimized with gradient-based attacks. While novel attacks are continuously proposed, each is shown to outperform its predecessors using differen…
Class Adaptive Network Calibration
Bingyuan Liu, Jérôme Rony, Adrian Galdran +2
Recent studies have revealed that, beyond conventional accuracy, calibration should also be considered for training modern deep neural networks. To address miscalibration during le…
Proximal Splitting Adversarial Attacks for Semantic Segmentation
Jérôme Rony, Jean-Christophe Pesquet, Ismail Ben Ayed
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 segmentatio…
Leveraging Uncertainty for Deep Interpretable Classification and Weakly-Supervised Segmentation of Histology Images
Soufiane Belharbi, Jérôme Rony, Jose Dolz +3
Trained using only image class label, deep weakly supervised methods allow image classification and ROI segmentation for interpretability. Despite their success on natural images,…
Mutual-Information Based Few-Shot Classification
Malik Boudiaf, Ziko Imtiaz Masud, Jérôme Rony +3
We introduce Transductive Infomation Maximization (TIM) for few-shot learning. Our method maximizes the mutual information between the query features and their label predictions fo…
Augmented Lagrangian Adversarial Attacks
Jérôme Rony, Eric Granger, Marco Pedersoli +1
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 propert…
Deep Interpretable Classification and Weakly-Supervised Segmentation of Histology Images via Max-Min Uncertainty
Soufiane Belharbi, Jérôme Rony, Jose Dolz +3
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-…
Transductive Information Maximization For Few-Shot Learning
Malik Boudiaf, Ziko Imtiaz Masud, Jérôme Rony +3
We introduce Transductive Infomation Maximization (TIM) for few-shot learning. Our method maximizes the mutual information between the query features and their label predictions fo…
A unifying mutual information view of metric learning: cross-entropy vs. pairwise losses
Malik Boudiaf, Jérôme Rony, Imtiaz Masud Ziko +4
Recently, substantial research efforts in Deep Metric Learning (DML) focused on designing complex pairwise-distance losses, which require convoluted schemes to ease optimization, s…
Deep Weakly-Supervised Learning Methods for Classification and Localization in Histology Images: A Survey
Jérôme Rony, Soufiane Belharbi, Jose Dolz +3
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 normall…
Universal Adversarial Audio Perturbations
Sajjad Abdoli, Luiz G. Hafemann, Jerome Rony +3
We demonstrate the existence of universal adversarial perturbations, which can fool a family of audio classification architectures, for both targeted and untargeted attack scenario…
Min-max Entropy for Weakly Supervised Pointwise Localization
Soufiane Belharbi, Jérôme Rony, Jose Dolz +3
Pointwise localization allows more precise localization and accurate interpretability, compared to bounding box, in applications where objects are highly unstructured such as in me…
Decoupling Direction and Norm for Efficient Gradient-Based L2 Adversarial Attacks and Defenses
Jérôme Rony, Luiz G. Hafemann, Luiz S. Oliveira +3
Research on adversarial examples in computer vision tasks has shown that small, often imperceptible changes to an image can induce misclassification, which has security implication…
Multi-region segmentation of bladder cancer structures in MRI with progressive dilated convolutional networks
Jose Dolz, Xiaopan Xu, Jerome Rony +7
Precise segmentation of bladder walls and tumor regions is an essential step towards non-invasive identification of tumor stage and grade, which is critical for treatment decision…