Search Results for author: Ismail Ben Ayed

Found 100 papers, 71 papers with code

Exploring the Transferability of a Foundation Model for Fundus Images: Application to Hypertensive Retinopathy

no code implementations27 Jan 2024 Julio Silva-Rodriguez, Jihed Chelbi, Waziha Kabir, Hadi Chakor, Jose Dolz, Ismail Ben Ayed, Riadh Kobbi

In this work, we explore the potential of using FLAIR features as starting point for fundus image classification, and we compare its performance with regard to Imagenet initialization on two popular transfer learning methods: Linear Probing (LP) and Fine-Tuning (FP).

Image Classification Medical Image Classification +1

Neighbor-Aware Calibration of Segmentation Networks with Penalty-Based Constraints

no code implementations25 Jan 2024 Balamurali Murugesan, Sukesh Adiga Vasudeva, Bingyuan Liu, Hervé Lombaert, Ismail Ben Ayed, Jose Dolz

Ensuring reliable confidence scores from deep neural networks is of paramount significance in critical decision-making systems, particularly in real-world domains such as healthcare.

Decision Making Segmentation

A Closer Look at the Few-Shot Adaptation of Large Vision-Language Models

1 code implementation20 Dec 2023 Julio Silva-Rodriguez, Sina Hajimiri, Ismail Ben Ayed, Jose Dolz

Efficient transfer learning (ETL) is receiving increasing attention to adapt large pre-trained language-vision models on downstream tasks with a few labeled samples.

Transfer Learning

Transductive Learning for Textual Few-Shot Classification in API-based Embedding Models

no code implementations21 Oct 2023 Pierre Colombo, Victor Pellegrain, Malik Boudiaf, Victor Storchan, Myriam Tami, Ismail Ben Ayed, Celine Hudelot, Pablo Piantanida

First, we introduce a scenario where the embedding of a pre-trained model is served through a gated API with compute-cost and data-privacy constraints.

Classification Transductive Learning

Aggregated f-average Neural Network for Interpretable Ensembling

no code implementations9 Oct 2023 Mathieu Vu, Emilie Chouzenoux, Jean-Christophe Pesquet, Ismail Ben Ayed

Ensemble learning leverages multiple models (i. e., weak learners) on a common machine learning task to enhance prediction performance.

Ensemble Learning Few-Shot Class-Incremental Learning +1

Bag of Tricks for Fully Test-Time Adaptation

1 code implementation3 Oct 2023 Saypraseuth Mounsaveng, Florent Chiaroni, Malik Boudiaf, Marco Pedersoli, Ismail Ben Ayed

Fully Test-Time Adaptation (TTA), which aims at adapting models to data drifts, has recently attracted wide interest.

Test-time Adaptation

A Foundation LAnguage-Image model of the Retina (FLAIR): Encoding expert knowledge in text supervision

1 code implementation15 Aug 2023 Julio Silva-Rodriguez, Hadi Chakor, Riadh Kobbi, Jose Dolz, Ismail Ben Ayed

Foundation vision-language models are currently transforming computer vision, and are on the rise in medical imaging fueled by their very promising generalization capabilities.

Descriptive Language Modelling

Automatic Data Augmentation Learning using Bilevel Optimization for Histopathological Images

1 code implementation21 Jul 2023 Saypraseuth Mounsaveng, Issam Laradji, David Vázquez, Marco Perdersoli, Ismail Ben Ayed

Experimental results show that our model can learn color and affine transformations that are more helpful to train an image classifier than predefined DA transformations, which are also more expensive as they need to be selected before the training by grid search on a validation set.

Bilevel Optimization Data Augmentation

Prompting classes: Exploring the Power of Prompt Class Learning in Weakly Supervised Semantic Segmentation

2 code implementations30 Jun 2023 Balamurali Murugesan, Rukhshanda Hussain, Rajarshi Bhattacharya, Ismail Ben Ayed, Jose Dolz

First, modifying only the class token of the text prompt results in a greater impact on the Class Activation Map (CAM), compared to arguably more complex strategies that optimize the context.

Few-Shot Learning Weakly supervised Semantic Segmentation +1

Task Adaptive Feature Transformation for One-Shot Learning

no code implementations13 Apr 2023 Imtiaz Masud Ziko, Freddy Lecue, Ismail Ben Ayed

We introduce a simple non-linear embedding adaptation layer, which is fine-tuned on top of fixed pre-trained features for one-shot tasks, improving significantly transductive entropy-based inference for low-shot regimes.

One-Shot Learning

Towards foundation models and few-shot parameter-efficient fine-tuning for volumetric organ segmentation

1 code implementation29 Mar 2023 Julio Silva-Rodríguez, Jose Dolz, Ismail Ben Ayed

With the recent raise of foundation models in computer vision and NLP, the pretrain-and-adapt strategy, where a large-scale model is fine-tuned on downstream tasks, is gaining popularity.

Image Segmentation Medical Image Segmentation +3

TFS-ViT: Token-Level Feature Stylization for Domain Generalization

1 code implementation28 Mar 2023 Mehrdad Noori, Milad Cheraghalikhani, Ali Bahri, Gustavo A. Vargas Hakim, David Osowiechi, Ismail Ben Ayed, Christian Desrosiers

This paper presents a first Token-level Feature Stylization (TFS-ViT) approach for domain generalization, which improves the performance of ViTs to unseen data by synthesizing new domains.

Domain Generalization

CoLo-CAM: Class Activation Mapping for Object Co-Localization in Weakly-Labeled Unconstrained Videos

1 code implementation16 Mar 2023 Soufiane Belharbi, Shakeeb Murtaza, Marco Pedersoli, Ismail Ben Ayed, Luke McCaffrey, Eric Granger

This paper proposes a novel CAM method for WSVOL that exploits spatiotemporal information in activation maps during training without constraining an object's position.

Object Object Localization

Trust your neighbours: Penalty-based constraints for model calibration

1 code implementation11 Mar 2023 Balamurali Murugesan, Sukesh Adiga V, Bingyuan Liu, Hervé Lombaert, Ismail Ben Ayed, Jose Dolz

Ensuring reliable confidence scores from deep networks is of pivotal importance in critical decision-making systems, notably in the medical domain.

Decision Making

Open-Set Likelihood Maximization for Few-Shot Learning

1 code implementation CVPR 2023 Malik Boudiaf, Etienne Bennequin, Myriam Tami, Antoine Toubhans, Pablo Piantanida, Céline Hudelot, Ismail Ben Ayed

We tackle the Few-Shot Open-Set Recognition (FSOSR) problem, i. e. classifying instances among a set of classes for which we only have a few labeled samples, while simultaneously detecting instances that do not belong to any known class.

Few-Shot Image Classification Few-Shot Learning +2

Proximal Splitting Adversarial Attack for Semantic Segmentation

1 code implementation CVPR 2023 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 segmentation.

Adversarial Attack Segmentation +1

Connectivity-constrained Interactive Panoptic Segmentation

no code implementations13 Dec 2022 Ruobing Shen, Bo Tang, Andrea Lodi, Ismail Ben Ayed, Thomas Guthier

We address interactive panoptic annotation, where one segment all object and stuff regions in an image.

Panoptic Segmentation Segmentation

Parametric Information Maximization for Generalized Category Discovery

1 code implementation ICCV 2023 Florent Chiaroni, Jose Dolz, Ziko Imtiaz Masud, Amar Mitiche, Ismail Ben Ayed

We introduce a Parametric Information Maximization (PIM) model for the Generalized Category Discovery (GCD) problem.

Class Adaptive Network Calibration

1 code implementation CVPR 2023 Bingyuan Liu, Jérôme Rony, Adrian Galdran, Jose Dolz, Ismail Ben Ayed

Comprehensive evaluation and multiple comparisons on a variety of benchmarks, including standard and long-tailed image classification, semantic segmentation, and text classification, demonstrate the superiority of the proposed method.

Image Classification Semantic Segmentation +2

Towards Practical Few-Shot Query Sets: Transductive Minimum Description Length Inference

1 code implementation26 Oct 2022 Ségolène Martin, Malik Boudiaf, Emilie Chouzenoux, Jean-Christophe Pesquet, Ismail Ben Ayed

We relax these assumptions and extend current benchmarks, so that the query-set classes of a given task are unknown, but just belong to a much larger set of possible classes.

Calibrating Segmentation Networks with Margin-based Label Smoothing

1 code implementation9 Sep 2022 Balamurali Murugesan, Bingyuan Liu, Adrian Galdran, Ismail Ben Ayed, Jose Dolz

Following our observations, we propose a simple and flexible generalization based on inequality constraints, which imposes a controllable margin on logit distances.

Image Segmentation Medical Image Segmentation +1

TCAM: Temporal Class Activation Maps for Object Localization in Weakly-Labeled Unconstrained Videos

1 code implementation30 Aug 2022 Soufiane Belharbi, Ismail Ben Ayed, Luke McCaffrey, Eric Granger

Our proposed TCAM method achieves a new state-of-art in WSVOL accuracy, and visual results suggest that it can be adapted for subsequent tasks like visual object tracking and detection.

Object Object Localization +2

Simplex Clustering via sBeta with Applications to Online Adjustment of Black-Box Predictions

1 code implementation30 Jul 2022 Florent Chiaroni, Malik Boudiaf, Amar Mitiche, Ismail Ben Ayed

We explore clustering the softmax predictions of deep neural networks and introduce a novel probabilistic clustering method, referred to as k-sBetas.

Clustering Descriptive +1

Model-Agnostic Few-Shot Open-Set Recognition

1 code implementation18 Jun 2022 Malik Boudiaf, Etienne Bennequin, Myriam Tami, Celine Hudelot, Antoine Toubhans, Pablo Piantanida, Ismail Ben Ayed

Through extensive experiments spanning 5 datasets, we show that OSTIM surpasses both inductive and existing transductive methods in detecting open-set instances while competing with the strongest transductive methods in classifying closed-set instances.

Few-Shot Learning Open Set Learning

Proximal Splitting Adversarial Attacks for Semantic Segmentation

1 code implementation14 Jun 2022 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 segmentation.

Adversarial Attack Segmentation +1

FHIST: A Benchmark for Few-shot Classification of Histological Images

no code implementations31 May 2022 Fereshteh Shakeri, Malik Boudiaf, Sina Mohammadi, Ivaxi Sheth, Mohammad Havaei, Ismail Ben Ayed, Samira Ebrahimi Kahou

We build few-shot tasks and base-training data with various tissue types, different levels of domain shifts stemming from various cancer sites, and different class-granularity levels, thereby reflecting realistic scenarios.

Classification Few-Shot Learning +1

Test-Time Adaptation with Shape Moments for Image Segmentation

1 code implementation16 May 2022 Mathilde Bateson, Hervé Lombaert, Ismail Ben Ayed

In typical clinical settings, the source data is inaccessible and the target distribution is represented with a handful of samples: adaptation can only happen at test time on a few or even a single subject(s).

Cardiac Segmentation Image Segmentation +3

Realistic Evaluation of Transductive Few-Shot Learning

1 code implementation NeurIPS 2021 Olivier Veilleux, Malik Boudiaf, Pablo Piantanida, Ismail Ben Ayed

Transductive inference is widely used in few-shot learning, as it leverages the statistics of the unlabeled query set of a few-shot task, typically yielding substantially better performances than its inductive counterpart.

Few-Shot Learning

Parameter-free Online Test-time Adaptation

1 code implementation CVPR 2022 Malik Boudiaf, Romain Mueller, Ismail Ben Ayed, Luca Bertinetto

An interesting and practical paradigm is online test-time adaptation, according to which training data is inaccessible, no labelled data from the test distribution is available, and adaptation can only happen at test time and on a handful of samples.

Test-time Adaptation

The Devil is in the Margin: Margin-based Label Smoothing for Network Calibration

1 code implementation CVPR 2022 Bingyuan Liu, Ismail Ben Ayed, Adrian Galdran, Jose Dolz

Following our observations, we propose a simple and flexible generalization based on inequality constraints, which imposes a controllable margin on logit distances.

Image Classification Semantic Segmentation

Segmentation with mixed supervision: Confidence maximization helps knowledge distillation

2 code implementations21 Sep 2021 Bingyuan Liu, Christian Desrosiers, Ismail Ben Ayed, Jose Dolz

Combined with a standard cross-entropy loss over the labeled pixels, our novel formulation integrates two important terms: (i) a Shannon entropy loss defined over the less-supervised images, which encourages confident student predictions in the bottom branch; and (ii) a KL divergence term, which transfers the knowledge (i. e., predictions) of the strongly supervised branch to the less-supervised branch and guides the entropy (student-confidence) term to avoid trivial solutions.

Image Segmentation Knowledge Distillation +2

F-CAM: Full Resolution Class Activation Maps via Guided Parametric Upscaling

1 code implementation15 Sep 2021 Soufiane Belharbi, Aydin Sarraf, Marco Pedersoli, Ismail Ben Ayed, Luke McCaffrey, Eric Granger

Interpolation is required to restore full size CAMs, yet it does not consider the statistical properties of objects, such as color and texture, leading to activations with inconsistent boundaries, and inaccurate localizations.

Weakly-Supervised Object Localization

Source-Free Domain Adaptation for Image Segmentation

1 code implementation6 Aug 2021 Mathilde Bateson, Hoel Kervadec, Jose Dolz, Hervé Lombaert, Ismail Ben Ayed

Our method yields comparable results to several state of the art adaptation techniques, despite having access to much less information, as the source images are entirely absent in our adaptation phase.

Cardiac Segmentation Image Segmentation +3

Mutual-Information Based Few-Shot Classification

3 code implementations23 Jun 2021 Malik Boudiaf, Ziko Imtiaz Masud, Jérôme Rony, Jose Dolz, Ismail Ben Ayed, Pablo Piantanida

We motivate our transductive loss by deriving a formal relation between the classification accuracy and mutual-information maximization.

Benchmarking Classification +1

Transductive Few-Shot Learning: Clustering is All You Need?

1 code implementation16 Jun 2021 Imtiaz Masud Ziko, Malik Boudiaf, Jose Dolz, Eric Granger, Ismail Ben Ayed

Surprisingly, we found that even standard clustering procedures (e. g., K-means), which correspond to particular, non-regularized cases of our general model, already achieve competitive performances in comparison to the state-of-the-art in few-shot learning.

Clustering Few-Shot Learning

Adversarial Robustness via Fisher-Rao Regularization

1 code implementation12 Jun 2021 Marine Picot, Francisco Messina, Malik Boudiaf, Fabrice Labeau, Ismail Ben Ayed, Pablo Piantanida

Adversarial robustness has become a topic of growing interest in machine learning since it was observed that neural networks tend to be brittle.

Adversarial Defense Adversarial Robustness

Beyond pixel-wise supervision for segmentation: A few global shape descriptors might be surprisingly good!

1 code implementation3 May 2021 Hoel Kervadec, Houda Bahig, Laurent Letourneau-Guillon, Jose Dolz, Ismail Ben Ayed

We also found that shape descriptors can be a valid way to encode anatomical priors about the task, enabling to leverage expert knowledge without additional annotations.

Image Segmentation Medical Image Segmentation +2

Do We Really Need Dice? The Hidden Region-Size Biases of Segmentation Losses

1 code implementation18 Apr 2021 Bingyuan Liu, Jose Dolz, Adrian Galdran, Riadh Kobbi, Ismail Ben Ayed

Most segmentation losses are arguably variants of the Cross-Entropy (CE) or Dice losses.

Teach me to segment with mixed supervision: Confident students become masters

1 code implementation15 Dec 2020 Jose Dolz, Christian Desrosiers, Ismail Ben Ayed

In conjunction with a standard cross-entropy over the labeled pixels, our novel formulation integrates two important terms: (i) a Shannon entropy loss defined over the less-supervised images, which encourages confident student predictions at the bottom branch; and (ii) a Kullback-Leibler (KL) divergence, which transfers the knowledge from the predictions generated by the strongly supervised branch to the less-supervised branch, and guides the entropy (student-confidence) term to avoid trivial solutions.

Semantic Segmentation

Few-Shot Segmentation Without Meta-Learning: A Good Transductive Inference Is All You Need?

2 code implementations CVPR 2021 Malik Boudiaf, Hoel Kervadec, Ziko Imtiaz Masud, Pablo Piantanida, Ismail Ben Ayed, Jose Dolz

We show that the way inference is performed in few-shot segmentation tasks has a substantial effect on performances -- an aspect often overlooked in the literature in favor of the meta-learning paradigm.

Few-Shot Semantic Segmentation

Augmented Lagrangian Adversarial Attacks

2 code implementations ICCV 2021 Jérôme Rony, Eric Granger, Marco Pedersoli, Ismail Ben Ayed

Our attack enjoys the generality of penalty methods and the computational efficiency of distance-customized algorithms, and can be readily used for a wide set of distances.

Adversarial Attack Computational Efficiency

Deep Interpretable Classification and Weakly-Supervised Segmentation of Histology Images via Max-Min Uncertainty

2 code implementations14 Nov 2020 Soufiane Belharbi, Jérôme Rony, Jose Dolz, Ismail Ben Ayed, Luke McCaffrey, Eric Granger

We propose novel regularization terms, which enable the model to seek both non-discriminative and discriminative regions, while discouraging unbalanced segmentations.

General Classification Weakly-supervised Learning +1

Deep Active Learning for Joint Classification & Segmentation with Weak Annotator

1 code implementation10 Oct 2020 Soufiane Belharbi, Ismail Ben Ayed, Luke McCaffrey, Eric Granger

CNN visualization and interpretation methods, like class-activation maps (CAMs), are typically used to highlight the image regions linked to class predictions.

Active Learning Classification +3

Cost-Sensitive Regularization for Diabetic Retinopathy Grading from Eye Fundus Images

1 code implementation1 Oct 2020 Adrian Galdran, José Dolz, Hadi Chakor, Hervé Lombaert, Ismail Ben Ayed

Assessing the degree of disease severity in biomedical images is a task similar to standard classification but constrained by an underlying structure in the label space.

Diabetic Retinopathy Grading General Classification

The Little W-Net That Could: State-of-the-Art Retinal Vessel Segmentation with Minimalistic Models

2 code implementations3 Sep 2020 Adrian Galdran, André Anjos, José Dolz, Hadi Chakor, Hervé Lombaert, Ismail Ben Ayed

Our analysis demonstrates that the retinal vessel segmentation problem is far from solved when considering test images that differ substantially from the training data, and that this task represents an ideal scenario for the exploration of domain adaptation techniques.

Domain Adaptation Retinal Vessel Segmentation +1

A Flow-Guided Mutual Attention Network for Video-Based Person Re-Identification

no code implementations9 Aug 2020 Madhu Kiran, Amran Bhuiyan, Louis-Antoine Blais-Morin, Mehrsan Javan, Ismail Ben Ayed, Eric Granger

Our Mutual Attention network relies on the joint spatial attention between image and optical flow features maps to activate a common set of salient features across them.

Optical Flow Estimation Video-Based Person Re-Identification

Medical Imaging with Deep Learning: MIDL 2020 -- Short Paper Track

no code implementations29 Jun 2020 Tal Arbel, Ismail Ben Ayed, Marleen de Bruijne, Maxime Descoteaux, Herve Lombaert, Chris Pal

This compendium gathers all the accepted extended abstracts from the Third International Conference on Medical Imaging with Deep Learning (MIDL 2020), held in Montreal, Canada, 6-9 July 2020.

BIG-bench Machine Learning

Laplacian Regularized Few-Shot Learning

2 code implementations28 Jun 2020 Imtiaz Masud Ziko, Jose Dolz, Eric Granger, Ismail Ben Ayed

Our transductive inference does not re-train the base model, and can be viewed as a graph clustering of the query set, subject to supervision constraints from the support set.

Clustering Few-Shot Image Classification +2

Source-Relaxed Domain Adaptation for Image Segmentation

5 code implementations7 May 2020 Mathilde Bateson, Hoel Kervadec, Jose Dolz, Herve Lombaert, Ismail Ben Ayed

Our formulation is based on minimizing a label-free entropy loss defined over target-domain data, which we further guide with a domain invariant prior on the segmentation regions.

Domain Adaptation Image Segmentation +2

A unifying mutual information view of metric learning: cross-entropy vs. pairwise losses

1 code implementation ECCV 2020 Malik Boudiaf, Jérôme Rony, Imtiaz Masud Ziko, Eric Granger, Marco Pedersoli, Pablo Piantanida, Ismail Ben Ayed

Second, we show that, more generally, minimizing the cross-entropy is actually equivalent to maximizing the mutual information, to which we connect several well-known pairwise losses.

Ranked #11 on Metric Learning on CARS196 (using extra training data)

Metric Learning

Semi-supervised few-shot learning for medical image segmentation

no code implementations18 Mar 2020 Abdur R Feyjie, Reza Azad, Marco Pedersoli, Claude Kauffman, Ismail Ben Ayed, Jose Dolz

To handle this new learning paradigm, we propose to include surrogate tasks that can leverage very powerful supervisory signals --derived from the data itself-- for semantic feature learning.

Few-Shot Learning Image Segmentation +4

On the Texture Bias for Few-Shot CNN Segmentation

1 code implementation9 Mar 2020 Reza Azad, Abdur R Fayjie, Claude Kauffman, Ismail Ben Ayed, Marco Pedersoli, Jose Dolz

Despite the initial belief that Convolutional Neural Networks (CNNs) are driven by shapes to perform visual recognition tasks, recent evidence suggests that texture bias in CNNs provides higher performing models when learning on large labeled training datasets.

Few-Shot Semantic Segmentation Segmentation +1

Non-parametric Uni-modality Constraints for Deep Ordinal Classification

1 code implementation25 Nov 2019 Soufiane Belharbi, Ismail Ben Ayed, Luke McCaffrey, Eric Granger

We propose a new constrained-optimization formulation for deep ordinal classification, in which uni-modality of the label distribution is enforced implicitly via a set of inequality constraints over all the pairs of adjacent labels.

 Ranked #1 on Historical Color Image Dating on HCI (MAE metric)

Classification General Classification +2

Connectivity-constrained interactive annotations for panoptic segmentation

no code implementations25 Sep 2019 Ruobing Shen, Bo Tang, Ismail Ben Ayed, Andrea Lodi, Thomas Guthier

Large-scale ground truth data sets are of crucial importance for deep learning based segmentation models, but annotating per-pixel masks is prohibitively time consuming.

Panoptic Segmentation Segmentation +1

Adversarial Learning of General Transformations for Data Augmentation

no code implementations ICLR Workshop LLD 2019 Saypraseuth Mounsaveng, David Vazquez, Ismail Ben Ayed, Marco Pedersoli

Data augmentation (DA) is fundamental against overfitting in large convolutional neural networks, especially with a limited training dataset.

Data Augmentation

Deep Weakly-Supervised Learning Methods for Classification and Localization in Histology Images: A Survey

1 code implementation8 Sep 2019 Jérôme Rony, Soufiane Belharbi, Jose Dolz, Ismail Ben Ayed, Luke McCaffrey, Eric Granger

Four key challenges are identified for the application of deep WSOL methods in histology -- under/over activation of CAMs, sensitivity to thresholding, and model selection.

General Classification Model Selection +2

Discretely-constrained deep network for weakly supervised segmentation

no code implementations15 Aug 2019 Jizong Peng, Hoel Kervadec, Jose Dolz, Ismail Ben Ayed, Marco Pedersoli, Christian Desrosiers

An efficient strategy for weakly-supervised segmentation is to impose constraints or regularization priors on target regions.

Cardiac Segmentation Segmentation +1

Universal Adversarial Audio Perturbations

1 code implementation arXiv preprint 2019 Sajjad Abdoli, Luiz G. Hafemann, Jerome Rony, Ismail Ben Ayed, Patrick Cardinal, Alessandro L. Koerich

We demonstrate the existence of universal adversarial perturbations, which can fool a family of audio classification architectures, for both targeted and untargeted attack scenarios.

Audio Classification

Constrained domain adaptation for Image segmentation

1 code implementation8 Aug 2019 Mathilde Bateson, Jose Dolz, Hoel Kervadec, Hervé Lombaert, Ismail Ben Ayed

We propose to adapt segmentation networks with a constrained formulation, which embeds domain-invariant prior knowledge about the segmentation regions.

Domain Adaptation Image Segmentation +2

Min-max Entropy for Weakly Supervised Pointwise Localization

1 code implementation25 Jul 2019 Soufiane Belharbi, Jérôme Rony, Jose Dolz, Ismail Ben Ayed, Luke McCaffrey, Eric Granger

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.

Weakly-Supervised Object Localization

Exploiting Prunability for Person Re-Identification

no code implementations4 Jul 2019 Hugo Masson, Amran Bhuiyan, Le Thanh Nguyen-Meidine, Mehrsan Javan, Parthipan Siva, Ismail Ben Ayed, Eric Granger

Then, these techniques are analysed according to their pruningcriteria and strategy, and according to different scenarios for exploiting pruningmethods to fine-tuning networks to target domains.

Person Re-Identification

Variational Fair Clustering

1 code implementation19 Jun 2019 Imtiaz Masud Ziko, Eric Granger, Jing Yuan, Ismail Ben Ayed

We derive a general tight upper bound based on a concave-convex decomposition of our fairness term, its Lipschitz-gradient property and the Pinsker's inequality.

Clustering Fairness

Curriculum semi-supervised segmentation

1 code implementation10 Apr 2019 Hoel Kervadec, Jose Dolz, Eric Granger, Ismail Ben Ayed

This study investigates a curriculum-style strategy for semi-supervised CNN segmentation, which devises a regression network to learn image-level information such as the size of a target region.

Left Ventricle Segmentation regression +2

Constrained Deep Networks: Lagrangian Optimization via Log-Barrier Extensions

1 code implementation8 Apr 2019 Hoel Kervadec, Jose Dolz, Jing Yuan, Christian Desrosiers, Eric Granger, Ismail Ben Ayed

While sub-optimality is not guaranteed for non-convex problems, this result shows that log-barrier extensions are a principled way to approximate Lagrangian optimization for constrained CNNs via implicit dual variables.

Image Segmentation Semantic Segmentation +2

Decoupling Direction and Norm for Efficient Gradient-Based L2 Adversarial Attacks and Defenses

5 code implementations23 Nov 2018 Jérôme Rony, Luiz G. Hafemann, Luiz S. Oliveira, Ismail Ben Ayed, Robert Sabourin, Eric Granger

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.

IVD-Net: Intervertebral disc localization and segmentation in MRI with a multi-modal UNet

1 code implementation19 Nov 2018 Jose Dolz, Christian Desrosiers, Ismail Ben Ayed

Despite the technological advances in medical imaging, IVD localization and segmentation are still manually performed, which is time-consuming and prone to errors.

Medical Image Segmentation Segmentation

Scalable Laplacian K-modes

1 code implementation NeurIPS 2018 Imtiaz Masud Ziko, Eric Granger, Ismail Ben Ayed

Furthermore, we show that the density modes can be obtained as byproducts of the assignment variables via simple maximum-value operations whose additional computational cost is linear in the number of data points.

Clustering valid

Dense Multi-path U-Net for Ischemic Stroke Lesion Segmentation in Multiple Image Modalities

no code implementations16 Oct 2018 Jose Dolz, Ismail Ben Ayed, Christian Desrosiers

First, instead of combining the available image modalities at the input, each of them is processed in a different path to better exploit their unique information.

Ischemic Stroke Lesion Segmentation Lesion Segmentation

Deep clustering: On the link between discriminative models and K-means

1 code implementation9 Oct 2018 Mohammed Jabi, Marco Pedersoli, Amar Mitiche, Ismail Ben Ayed

Typically, they use multinomial logistic regression posteriors and parameter regularization, as is very common in supervised learning.

Clustering Deep Clustering +2

Beyond Gradient Descent for Regularized Segmentation Losses

1 code implementation CVPR 2019 Dmitrii Marin, Meng Tang, Ismail Ben Ayed, Yuri Boykov

Both loss functions and architectures are often explicitly tuned to be amenable to this basic local optimization.

Segmentation

Multi-region segmentation of bladder cancer structures in MRI with progressive dilated convolutional networks

no code implementations28 May 2018 Jose Dolz, Xiaopan Xu, Jerome Rony, Jing Yuan, Yang Liu, Eric Granger, Christian Desrosiers, Xi Zhang, Ismail Ben Ayed, Hongbing Lu

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 and prognosis of patients with bladder cancer (BC).

Segmentation

Constrained-CNN losses for weakly supervised segmentation

4 code implementations12 May 2018 Hoel Kervadec, Jose Dolz, Meng Tang, Eric Granger, Yuri Boykov, Ismail Ben Ayed

To the best of our knowledge, the method of [Pathak et al., 2015] is the only prior work that addresses deep CNNs with linear constraints in weakly supervised segmentation.

Medical Image Segmentation Segmentation +3

HyperDense-Net: A hyper-densely connected CNN for multi-modal image segmentation

3 code implementations9 Apr 2018 Jose Dolz, Karthik Gopinath, Jing Yuan, Herve Lombaert, Christian Desrosiers, Ismail Ben Ayed

Therefore, the proposed network has total freedom to learn more complex combinations between the modalities, within and in-between all the levels of abstraction, which increases significantly the learning representation.

Brain Segmentation Image Classification +5

On Regularized Losses for Weakly-supervised CNN Segmentation

no code implementations ECCV 2018 Meng Tang, Federico Perazzi, Abdelaziz Djelouah, Ismail Ben Ayed, Christopher Schroers, Yuri Boykov

This approach simplifies weakly-supervised training by avoiding extra MRF/CRF inference steps or layers explicitly generating full masks, while improving both the quality and efficiency of training.

Segmentation Semantic Segmentation

An ILP Solver for Multi-label MRFs with Connectivity Constraints

no code implementations16 Dec 2017 Ruobing Shen, Eric Kendinibilir, Ismail Ben Ayed, Andrea Lodi, Andrea Tramontani, Gerhard Reinelt

The method enforces connectivity priors iteratively by a cutting plane method, and provides feasible solutions with a guarantee on sub-optimality even if we terminate it earlier.

Weakly supervised segmentation

Deep CNN ensembles and suggestive annotations for infant brain MRI segmentation

1 code implementation14 Dec 2017 Jose Dolz, Christian Desrosiers, Li Wang, Jing Yuan, Dinggang Shen, Ismail Ben Ayed

We report evaluations of our method on the public data of the MICCAI iSEG-2017 Challenge on 6-month infant brain MRI segmentation, and show very competitive results among 21 teams, ranking first or second in most metrics.

Image Segmentation Infant Brain Mri Segmentation +3

Isointense Infant Brain Segmentation with a Hyper-dense Connected Convolutional Neural Network

1 code implementation16 Oct 2017 Jose Dolz, Ismail Ben Ayed, Jing Yuan, Christian Desrosiers

Neonatal brain segmentation in magnetic resonance (MR) is a challenging problem due to poor image quality and low contrast between white and gray matter regions.

Brain Segmentation Infant Brain Mri Segmentation +2

Kernel clustering: density biases and solutions

no code implementations16 May 2017 Dmitrii Marin, Meng Tang, Ismail Ben Ayed, Yuri Boykov

We call it Breiman's bias due to its similarity to the histogram mode isolation previously discovered by Breiman in decision tree learning with Gini impurity.

Clustering

Unbiased Shape Compactness for Segmentation

1 code implementation28 Apr 2017 Jose Dolz, Ismail Ben Ayed, Christian Desrosiers

We propose to constrain segmentation functionals with a dimensionless, unbiased and position-independent shape compactness prior, which we solve efficiently with an alternating direction method of multipliers (ADMM).

Segmentation

A 3D fully convolutional neural network and a random walker to segment the esophagus in CT

no code implementations21 Apr 2017 Tobias Fechter, Sonja Adebahr, Dimos Baltas, Ismail Ben Ayed, Christian Desrosiers, Jose Dolz

These figures translate into a very good agreement with the reference contours and an increase in accuracy compared to other methods.

DOPE: Distributed Optimization for Pairwise Energies

no code implementations CVPR 2017 Jose Dolz, Ismail Ben Ayed, Christian Desrosiers

We formulate an Alternating Direction Method of Mul-tipliers (ADMM) that systematically distributes the computations of any technique for optimizing pairwise functions, including non-submodular potentials.

Distributed Optimization

Secrets of GrabCut and Kernel K-Means

no code implementations ICCV 2015 Meng Tang, Ismail Ben Ayed, Dmitrii Marin, Yuri Boykov

Our bound formulation for kernel K-means allows to combine general pair-wise feature clustering methods with image grid regularization using graph cuts, similarly to standard color model fitting techniques for segmentation.

Clustering Segmentation

Kernel Cuts: MRF meets Kernel & Spectral Clustering

no code implementations24 Jun 2015 Meng Tang, Dmitrii Marin, Ismail Ben Ayed, Yuri Boykov

We propose a new segmentation model combining common regularization energies, e. g. Markov Random Field (MRF) potentials, and standard pairwise clustering criteria like Normalized Cut (NC), average association (AA), etc.

Clustering

Volumetric Bias in Segmentation and Reconstruction: Secrets and Solutions

no code implementations ICCV 2015 Yuri Boykov, Hossam Isack, Carl Olsson, Ismail Ben Ayed

Many standard optimization methods for segmentation and reconstruction compute ML model estimates for appearance or geometry of segments, e. g. Zhu-Yuille 1996, Torr 1998, Chan-Vese 2001, GrabCut 2004, Delong et al. 2012.

Segmentation

Submodularization for Binary Pairwise Energies

no code implementations CVPR 2014 Lena Gorelick, Yuri Boykov, Olga Veksler, Ismail Ben Ayed, Andrew Delong

We propose a general optimization framework based on local submodular approximations (LSA).

Submodularization for Quadratic Pseudo-Boolean Optimization

no code implementations8 Nov 2013 Lena Gorelick, Yuri Boykov, Olga Veksler, Ismail Ben Ayed, Andrew Delong

We propose a general optimization framework based on local submodular approximations (LSA).

Auxiliary Cuts for General Classes of Higher Order Functionals

no code implementations CVPR 2013 Ismail Ben Ayed, Lena Gorelick, Yuri Boykov

From these general-form bounds, we state various non-linear problems as the optimization of auxiliary functionals by graph cuts.

Cannot find the paper you are looking for? You can Submit a new open access paper.