
MutualInformation Based FewShot Classification
We introduce Transductive Infomation Maximization (TIM) for fewshot lea...
read it

Adversarial Robustness via FisherRao Regularization
Adversarial robustness has become a topic of growing interest in machine...
read it

Beyond pixelwise supervision for segmentation: A few global shape descriptors might be surprisingly good!
Standard losses for training deep segmentation networks could be seen as...
read it

The hidden labelmarginal biases of segmentation losses
Most segmentation losses are arguably variants of the CrossEntropy (CE)...
read it

Teach me to segment with mixed supervision: Confident students become masters
Deep segmentation neural networks require large training datasets with p...
read it

FewShot Segmentation Without MetaLearning: A Good Transductive Inference Is All You Need?
Fewshot segmentation has recently attracted substantial interest, with ...
read it

AIDE: Annotationefficient deep learning for automatic medical image segmentation
Accurate image segmentation is crucial for medical imaging applications....
read it

CostSensitive Regularization for Diabetic Retinopathy Grading from Eye Fundus Images
Assessing the degree of disease severity in biomedical images is a task ...
read it

The Little WNet That Could: StateoftheArt Retinal Vessel Segmentation with Minimalistic Models
The segmentation of the retinal vasculature from eye fundus images repre...
read it

Transductive Information Maximization For FewShot Learning
We introduce Transductive Infomation Maximization (TIM) for fewshot lea...
read it

Learning Data Augmentation with Online Bilevel Optimization for Image Classification
Data augmentation is a key practice in machine learning for improving ge...
read it

SourceRelaxed Domain Adaptation for Image Segmentation
Domain adaptation (DA) has drawn high interests for its capacity to adap...
read it

Semisupervised fewshot learning for medical image segmentation
Recent years have witnessed the great progress of deep neural networks o...
read it

On the Texture Bias for FewShot CNN Segmentation
Despite the initial belief that Convolutional Neural Networks (CNNs) are...
read it

Adversarial Learning of General Transformations for Data Augmentation
Data augmentation (DA) is fundamental against overfitting in large convo...
read it

Deep weaklysupervised learning methods for classification and localization in histology images: a survey
Using stateoftheart deep learning models for the computerassisted di...
read it

Discretelyconstrained deep network for weakly supervised segmentation
An efficient strategy for weaklysupervised segmentation is to impose co...
read it

Universal Adversarial Audio Perturbations
We demonstrate the existence of universal adversarial perturbations, whi...
read it

Constrained domain adaptation for segmentation
We propose to adapt segmentation networks with a constrained formulation...
read it

Weakly Supervised Object Localization using MinMax Entropy: an Interpretable Framework
Weakly supervised object localization (WSOL) models aim to locate object...
read it

A Survey of Pruning Methods for Efficient Person Reidentification Across Domains
Recent years have witnessed a substantial increase in the deep learning ...
read it

Clustering with Fairness Constraints: A Flexible and Scalable Approach
This study investigates a general variational formulation of fair cluste...
read it

Curriculum semisupervised segmentation
This study investigates a curriculumstyle strategy for semisupervised ...
read it

Logbarrier constrained CNNs
This study investigates imposing inequality constraints on the outputs o...
read it

On Direct Distribution Matching for Adapting Segmentation Networks
Minimization of distribution matching losses is a principled approach to...
read it

Boundary loss for highly unbalanced segmentation
Widely used loss functions for convolutional neural network (CNN) segmen...
read it

Decoupling Direction and Norm for Efficient GradientBased L2 Adversarial Attacks and Defenses
Research on adversarial examples in computer vision tasks has shown that...
read it

IVDNet: Intervertebral disc localization and segmentation in MRI with a multimodal UNet
Accurate localization and segmentation of intervertebral disc (IVD) is c...
read it

Scalable Laplacian Kmodes
We advocate Laplacian Kmodes for joint clustering and density mode find...
read it

Dense Multipath UNet for Ischemic Stroke Lesion Segmentation in Multiple Image Modalities
Delineating infarcted tissue in ischemic stroke lesions is crucial to de...
read it

Deep clustering: On the link between discriminative models and Kmeans
In the context of recent deep clustering studies, discriminative models ...
read it

ADM for grid CRF loss in CNN segmentation
Variants of gradient descent (GD) dominate CNN loss minimization in comp...
read it

Multiregion segmentation of bladder cancer structures in MRI with progressive dilated convolutional networks
Precise segmentation of bladder walls and tumor regions is an essential ...
read it

ConstrainedCNN losses forweakly supervised segmentation
Weak supervision, e.g., in the form of partial labels or image tags, is ...
read it

HyperDenseNet: A hyperdensely connected CNN for multimodal image segmentation
Recently, dense connections have attracted substantial attention in comp...
read it

On Regularized Losses for Weaklysupervised CNN Segmentation
Minimization of regularized losses is a principled approach to weak supe...
read it

An ILP Solver for Multilabel MRFS with Connectivity Constraints
Integer Linear Programming (ILP) formulations of Markov random fields (M...
read it

Deep CNN ensembles and suggestive annotations for infant brain MRI segmentation
Precise 3D segmentation of infant brain tissues is an essential step tow...
read it

HyperDenseNet: A densely connected CNN for multimodal image segmentation
Neonatal brain segmentation in magnetic resonance (MR) is a challenging ...
read it

Kernel clustering: density biases and solutions
Kernel methods are popular in clustering due to their generality and dis...
read it

DOPE: Distributed Optimization for Pairwise Energies
We formulate an Alternating Direction Method of Multipliers (ADMM) that...
read it

Kernel Cuts: MRF meets Kernel & Spectral Clustering
We propose a new segmentation model combining common regularization ener...
read it

Volumetric Bias in Segmentation and Reconstruction: Secrets and Solutions
Many standard optimization methods for segmentation and reconstruction c...
read it

Submodularization for Quadratic PseudoBoolean Optimization
Many computer vision problems require optimization of binary nonsubmodu...
read it
Ismail Ben Ayed
is this you? claim profile
Associate Professor, Ecole de Technologie Superieure (ETS), ETS Research Chair on Artificial Intelligence in Medical Imaging