Search Results for author: Jean-Philippe Thiran

Found 55 papers, 21 papers with code

Uncertainty modeling for fine-tuned implicit functions

no code implementations17 Jun 2024 Anna Susmelj, Mael Macuglia, Nataša Tagasovska, Reto Sutter, Sebastiano Caprara, Jean-Philippe Thiran, Ender Konukoglu

In this paper, we introduce Dropsembles, a novel method for uncertainty estimation in tuned implicit functions.

Cross-Age and Cross-Site Domain Shift Impacts on Deep Learning-Based White Matter Fiber Estimation in Newborn and Baby Brains

no code implementations22 Dec 2023 Rizhong Lin, Ali Gholipour, Jean-Philippe Thiran, Davood Karimi, Hamza Kebiri, Meritxell Bach Cuadra

However, these models face domain shift challenges when test and train data are from different scanners and protocols, or when the models are applied to data with inherent variations such as the developing brains of infants and children scanned at various ages.

Domain Adaptation

CrIBo: Self-Supervised Learning via Cross-Image Object-Level Bootstrapping

1 code implementation11 Oct 2023 Tim Lebailly, Thomas Stegmüller, Behzad Bozorgtabar, Jean-Philippe Thiran, Tinne Tuytelaars

Leveraging nearest neighbor retrieval for self-supervised representation learning has proven beneficial with object-centric images.

In-Context Learning Object +3

AMAE: Adaptation of Pre-Trained Masked Autoencoder for Dual-Distribution Anomaly Detection in Chest X-Rays

no code implementations24 Jul 2023 Behzad Bozorgtabar, Dwarikanath Mahapatra, Jean-Philippe Thiran

Inspired by a modern self-supervised vision transformer model trained using partial image inputs to reconstruct missing image regions -- we propose AMAE, a two-stage algorithm for adaptation of the pre-trained masked autoencoder (MAE).

One-Class Classification Unsupervised Anomaly Detection

Distill-SODA: Distilling Self-Supervised Vision Transformer for Source-Free Open-Set Domain Adaptation in Computational Pathology

2 code implementations10 Jul 2023 Guillaume Vray, Devavrat Tomar, Jean-Philippe Thiran, Behzad Bozorgtabar

Developing computational pathology models is essential for reducing manual tissue typing from whole slide images, transferring knowledge from the source domain to an unlabeled, shifted target domain, and identifying unseen categories.

Data Augmentation Domain Adaptation +2

Fast refacing of MR images with a generative neural network lowers re-identification risk and preserves volumetric consistency

1 code implementation26 May 2023 Nataliia Molchanova, Bénédicte Maréchal, Jean-Philippe Thiran, Tobias Kober, Till Huelnhagen, Jonas Richiardi

To evaluate the performance of the proposed de-identification tool, a comparative study was conducted between several existing defacing and refacing tools, with two different segmentation algorithms (FAST and Morphobox).

Brain Morphometry De-identification +2

Neural Implicit Dense Semantic SLAM

no code implementations27 Apr 2023 Yasaman Haghighi, Suryansh Kumar, Jean-Philippe Thiran, Luc van Gool

Visual Simultaneous Localization and Mapping (vSLAM) is a widely used technique in robotics and computer vision that enables a robot to create a map of an unfamiliar environment using a camera sensor while simultaneously tracking its position over time.

Scene Understanding Semantic Segmentation +1

CrOC: Cross-View Online Clustering for Dense Visual Representation Learning

2 code implementations CVPR 2023 Thomas Stegmüller, Tim Lebailly, Behzad Bozorgtabar, Tinne Tuytelaars, Jean-Philippe Thiran

More importantly, the clustering algorithm conjointly operates on the features of both views, thereby elegantly bypassing the issue of content not represented in both views and the ambiguous matching of objects from one crop to the other.

Clustering Online Clustering +5

Adaptive Similarity Bootstrapping for Self-Distillation based Representation Learning

1 code implementation ICCV 2023 Tim Lebailly, Thomas Stegmüller, Behzad Bozorgtabar, Jean-Philippe Thiran, Tinne Tuytelaars

Most self-supervised methods for representation learning leverage a cross-view consistency objective i. e., they maximize the representation similarity of a given image's augmented views.

Contrastive Learning Representation Learning

TeSLA: Test-Time Self-Learning With Automatic Adversarial Augmentation

1 code implementation CVPR 2023 Devavrat Tomar, Guillaume Vray, Behzad Bozorgtabar, Jean-Philippe Thiran

Most recent test-time adaptation methods focus on only classification tasks, use specialized network architectures, destroy model calibration or rely on lightweight information from the source domain.

Knowledge Distillation Self-Learning +1

Microstructure estimation from diffusion-MRI: Compartmentalized models in permeable cellular tissue

no code implementations6 Sep 2022 Rémy Gardier, Juan Luis Villarreal Haro, Erick J Canales-Rodrıguez, Ileana O. Jelescu, Gabriel Girard, Jonathan Rafael-Patino, Jean-Philippe Thiran

Finally, the simulations performed in this work showed that the exchange between the intracellular and the extracellular space cannot be neglected in permeable tissue with a conventional PGSE sequence, to obtain accurate estimates.

ScoreNet: Learning Non-Uniform Attention and Augmentation for Transformer-Based Histopathological Image Classification

1 code implementation15 Feb 2022 Thomas Stegmüller, Behzad Bozorgtabar, Antoine Spahr, Jean-Philippe Thiran

We further introduce a novel mixing data-augmentation, namely ScoreMix, by leveraging the image's semantic distribution to guide the data mixing and produce coherent sample-label pairs.

Data Augmentation Domain Generalization +3

Validation and Generalizability of Self-Supervised Image Reconstruction Methods for Undersampled MRI

no code implementations29 Jan 2022 Thomas Yu, Tom Hilbert, Gian Franco Piredda, Arun Joseph, Gabriele Bonanno, Salim Zenkhri, Patrick Omoumi, Meritxell Bach Cuadra, Erick Jorge Canales-Rodríguez, Tobias Kober, Jean-Philippe Thiran

In this paper, we investigate important aspects of the validation of self-supervised algorithms for reconstruction of undersampled MR images: quantitative evaluation of prospective reconstructions, potential differences between prospective and retrospective reconstructions, suitability of commonly used quantitative metrics, and generalizability.

Anatomy Denoising +1

Cortical lesions, central vein sign, and paramagnetic rim lesions in multiple sclerosis: emerging machine learning techniques and future avenues

no code implementations19 Jan 2022 Francesco La Rosa, Maxence Wynen, Omar Al-Louzi, Erin S Beck, Till Huelnhagen, Pietro Maggi, Jean-Philippe Thiran, Tobias Kober, Russell T Shinohara, Pascal Sati, Daniel S Reich, Cristina Granziera, Martina Absinta, Meritxell Bach Cuadra

Recently, advanced MS lesional imaging biomarkers such as cortical lesions (CL), the central vein sign (CVS), and paramagnetic rim lesions (PRL), visible in specialized magnetic resonance imaging (MRI) sequences, have shown higher specificity in differential diagnosis.

Lesion Segmentation Specificity

Self-Supervised Generative Style Transfer for One-Shot Medical Image Segmentation

1 code implementation5 Oct 2021 Devavrat Tomar, Behzad Bozorgtabar, Manana Lortkipanidze, Guillaume Vray, Mohammad Saeed Rad, Jean-Philippe Thiran

Motivated by atlas-based segmentation, we propose a novel volumetric self-supervised learning for data augmentation capable of synthesizing volumetric image-segmentation pairs via learning transformations from a single labeled atlas to the unlabeled data.

Data Augmentation Image Segmentation +7

Self-Rule to Multi-Adapt: Generalized Multi-source Feature Learning Using Unsupervised Domain Adaptation for Colorectal Cancer Tissue Detection

1 code implementation20 Aug 2021 Christian Abbet, Linda Studer, Andreas Fischer, Heather Dawson, Inti Zlobec, Behzad Bozorgtabar, Jean-Philippe Thiran

In this work, we propose Self-Rule to Multi-Adapt (SRMA), which takes advantage of self-supervised learning to perform domain adaptation, and removes the necessity of fully-labeled source datasets.

Self-Supervised Learning Unsupervised Domain Adaptation

Test-Time Adaptation for Super-Resolution: You Only Need to Overfit on a Few More Images

no code implementations6 Apr 2021 Mohammad Saeed Rad, Thomas Yu, Behzad Bozorgtabar, Jean-Philippe Thiran

Addressing both issues, we propose a simple yet universal approach to improve the perceptual quality of the HR prediction from a pre-trained SR network on a given LR input by further fine-tuning the SR network on a subset of images from the training dataset with similar patterns of activation as the initial HR prediction, with respect to the filters of a feature extractor.

SSIM Super-Resolution +1

Self-Attentive Spatial Adaptive Normalization for Cross-Modality Domain Adaptation

1 code implementation5 Mar 2021 Devavrat Tomar, Manana Lortkipanidze, Guillaume Vray, Behzad Bozorgtabar, Jean-Philippe Thiran

We present a novel approach for image-to-image translation in medical images, capable of supervised or unsupervised (unpaired image data) setups.

Domain Adaptation Image-to-Image Translation +1

Hierarchical Graph Representations in Digital Pathology

4 code implementations22 Feb 2021 Pushpak Pati, Guillaume Jaume, Antonio Foncubierta, Florinda Feroce, Anna Maria Anniciello, Giosuè Scognamiglio, Nadia Brancati, Maryse Fiche, Estelle Dubruc, Daniel Riccio, Maurizio Di Bonito, Giuseppe De Pietro, Gerardo Botti, Jean-Philippe Thiran, Maria Frucci, Orcun Goksel, Maria Gabrani

We propose a novel multi-level hierarchical entity-graph representation of tissue specimens to model hierarchical compositions that encode histological entities as well as their intra- and inter-entity level interactions.

Graph Neural Network

Self-Taught Semi-Supervised Anomaly Detection on Upper Limb X-rays

1 code implementation19 Feb 2021 Antoine Spahr, Behzad Bozorgtabar, Jean-Philippe Thiran

Detecting anomalies in musculoskeletal radiographs is of paramount importance for large-scale screening in the radiology workflow.

Self-Supervised Anomaly Detection Semi-supervised Anomaly Detection +1

Quantifying Explainers of Graph Neural Networks in Computational Pathology

3 code implementations CVPR 2021 Guillaume Jaume, Pushpak Pati, Behzad Bozorgtabar, Antonio Foncubierta-Rodríguez, Florinda Feroce, Anna Maria Anniciello, Tilman Rau, Jean-Philippe Thiran, Maria Gabrani, Orcun Goksel

However, popular deep learning methods and explainability techniques (explainers) based on pixel-wise processing disregard biological entities' notion, thus complicating comprehension by pathologists.

Anomaly Detection on X-Rays Using Self-Supervised Aggregation Learning

no code implementations19 Oct 2020 Behzad Bozorgtabar, Dwarikanath Mahapatra, Guillaume Vray, Jean-Philippe Thiran

Deep anomaly detection models using a supervised mode of learning usually work under a closed set assumption and suffer from overfitting to previously seen rare anomalies at training, which hinders their applicability in a real scenario.

Anomaly Detection

CNN-Based Ultrasound Image Reconstruction for Ultrafast Displacement Tracking

no code implementations3 Sep 2020 Dimitris Perdios, Manuel Vonlanthen, Florian Martinez, Marcel Arditi, Jean-Philippe Thiran

Thanks to its capability of acquiring full-view frames at multiple kilohertz, ultrafast ultrasound imaging unlocked the analysis of rapidly changing physical phenomena in the human body, with pioneering applications such as ultrasensitive flow imaging in the cardiovascular system or shear-wave elastography.

Image Reconstruction Motion Estimation

CNN-Based Image Reconstruction Method for Ultrafast Ultrasound Imaging

1 code implementation28 Aug 2020 Dimitris Perdios, Manuel Vonlanthen, Florian Martinez, Marcel Arditi, Jean-Philippe Thiran

In vitro and in vivo experiments show that trainings carried out on simulated data perform well in experimental settings.

Image Reconstruction

Automated Detection of Cortical Lesions in Multiple Sclerosis Patients with 7T MRI

no code implementations15 Aug 2020 Francesco La Rosa, Erin S Beck, Ahmed Abdulkadir, Jean-Philippe Thiran, Daniel S. Reich, Pascal Sati, Meritxell Bach Cuadra

The automated detection of cortical lesions (CLs) in patients with multiple sclerosis (MS) is a challenging task that, despite its clinical relevance, has received very little attention.

Lesion Detection Segmentation

Structure Preserving Stain Normalization of Histopathology Images Using Self-Supervised Semantic Guidance

no code implementations5 Aug 2020 Dwarikanath Mahapatra, Behzad Bozorgtabar, Jean-Philippe Thiran, Ling Shao

Although generative adversarial network (GAN) based style transfer is state of the art in histopathology color-stain normalization, they do not explicitly integrate structural information of tissues.

Color Normalization Generative Adversarial Network +2

Divide-and-Rule: Self-Supervised Learning for Survival Analysis in Colorectal Cancer

1 code implementation7 Jul 2020 Christian Abbet, Inti Zlobec, Behzad Bozorgtabar, Jean-Philippe Thiran

In this work, we aim to learn histopathological patterns within cancerous tissue regions that can be used to improve prognostic stratification for colorectal cancer.

Clustering Deep Clustering +2

Benefiting from Bicubically Down-Sampled Images for Learning Real-World Image Super-Resolution

no code implementations6 Jul 2020 Mohammad Saeed Rad, Thomas Yu, Claudiu Musat, Hazim Kemal Ekenel, Behzad Bozorgtabar, Jean-Philippe Thiran

First, we train a network to transform real LR images to the space of bicubically downsampled images in a supervised manner, by using both real LR/HR pairs and synthetic pairs.

Image Super-Resolution

Towards Explainable Graph Representations in Digital Pathology

no code implementations1 Jul 2020 Guillaume Jaume, Pushpak Pati, Antonio Foncubierta-Rodriguez, Florinda Feroce, Giosue Scognamiglio, Anna Maria Anniciello, Jean-Philippe Thiran, Orcun Goksel, Maria Gabrani

Explainability of machine learning (ML) techniques in digital pathology (DP) is of great significance to facilitate their wide adoption in clinics.

Pathological Retinal Region Segmentation From OCT Images Using Geometric Relation Based Augmentation

no code implementations CVPR 2020 Dwarikanath Mahapatra, Behzad Bozorgtabar, Jean-Philippe Thiran, Ling Shao

The proposed method outperforms state-of-the-art segmentation methods on the public RETOUCH dataset having images captured from different acquisition procedures.

Data Augmentation Image Generation +5

Revisiting Few-Shot Learning for Facial Expression Recognition

no code implementations5 Dec 2019 Anca-Nicoleta Ciubotaru, Arnout Devos, Behzad Bozorgtabar, Jean-Philippe Thiran, Maria Gabrani

Most of the existing deep neural nets on automatic facial expression recognition focus on a set of predefined emotion classes, where the amount of training data has the biggest impact on performance.

Facial Expression Recognition Facial Expression Recognition (FER) +1

SROBB: Targeted Perceptual Loss for Single Image Super-Resolution

no code implementations ICCV 2019 Mohammad Saeed Rad, Behzad Bozorgtabar, Urs-Viktor Marti, Max Basler, Hazim Kemal Ekenel, Jean-Philippe Thiran

By benefiting from perceptual losses, recent studies have improved significantly the performance of the super-resolution task, where a high-resolution image is resolved from its low-resolution counterpart.

Decoder Image Super-Resolution

Benefiting from Multitask Learning to Improve Single Image Super-Resolution

no code implementations29 Jul 2019 Mohammad Saeed Rad, Behzad Bozorgtabar, Claudiu Musat, Urs-Viktor Marti, Max Basler, Hazim Kemal Ekenel, Jean-Philippe Thiran

Despite significant progress toward super resolving more realistic images by deeper convolutional neural networks (CNNs), reconstructing fine and natural textures still remains a challenging problem.

Decoder Image Super-Resolution +1

Exploring Factors for Improving Low Resolution Face Recognition

no code implementations23 Jul 2019 Omid Abdollahi Aghdam, Behzad Bozorgtabar, Hazim Kemal Ekenel, Jean-Philippe Thiran

By leveraging this information, we have utilized deep face models trained on MS-Celeb-1M and fine-tuned on VGGFace2 dataset and achieved state-of-the-art accuracies on the SCFace and ICB-RW benchmarks, even without using any training data from the datasets of these benchmarks.

Face Recognition

FUNSD: A Dataset for Form Understanding in Noisy Scanned Documents

3 code implementations27 May 2019 Guillaume Jaume, Hazim Kemal Ekenel, Jean-Philippe Thiran

We present a new dataset for form understanding in noisy scanned documents (FUNSD) that aims at extracting and structuring the textual content of forms.

Optical Character Recognition Optical Character Recognition (OCR) +1

Using Photorealistic Face Synthesis and Domain Adaptation to Improve Facial Expression Analysis

no code implementations17 May 2019 Behzad Bozorgtabar, Mohammad Saeed Rad, Hazim Kemal Ekenel, Jean-Philippe Thiran

Moreover, we also conduct experiments on a near-infrared dataset containing facial expression videos of drivers to assess the performance using in-the-wild data for driver emotion recognition.

Attribute Domain Adaptation +3

Learn to synthesize and synthesize to learn

1 code implementation1 May 2019 Behzad Bozorgtabar, Mohammad Saeed Rad, Hazim Kemal Ekenel, Jean-Philippe Thiran

To overcome these shortcomings, we propose attribute guided face image generation method using a single model, which is capable to synthesize multiple photo-realistic face images conditioned on the attributes of interest.

Attribute Data Augmentation +4

edGNN: a Simple and Powerful GNN for Directed Labeled Graphs

1 code implementation18 Apr 2019 Guillaume Jaume, An-phi Nguyen, María Rodríguez Martínez, Jean-Philippe Thiran, Maria Gabrani

The ability of a graph neural network (GNN) to leverage both the graph topology and graph labels is fundamental to building discriminative node and graph embeddings.

Graph Classification Graph Neural Network

Shallow vs deep learning architectures for white matter lesion segmentation in the early stages of multiple sclerosis

no code implementations10 Sep 2018 Francesco La Rosa, Mário João Fartaria, Tobias Kober, Jonas Richiardi, Cristina Granziera, Jean-Philippe Thiran, Meritxell Bach Cuadra

In this work, we present a comparison of a shallow and a deep learning architecture for the automated segmentation of white matter lesions in MR images of multiple sclerosis patients.

Lesion Segmentation Segmentation

Efficient Active Learning for Image Classification and Segmentation using a Sample Selection and Conditional Generative Adversarial Network

no code implementations14 Jun 2018 Dwarikanath Mahapatra, Behzad Bozorgtabar, Jean-Philippe Thiran, Mauricio Reyes

Training robust deep learning (DL) systems for medical image classification or segmentation is challenging due to limited images covering different disease types and severity.

Active Learning General Classification +3

Fast Fiber Orientation Estimation in Diffusion MRI from kq-Space Sampling and Anatomical Priors

no code implementations8 Feb 2018 Marica Pesce, Audrey Repetti, Anna Auría, Alessandro Daducci, Jean-Philippe Thiran, Yves Wiaux

High spatio-angular resolution diffusion MRI (dMRI) has been shown to provide accurate identification of complex neuronal fiber configurations, albeit, at the cost of long acquisition times.

Robust Real-Time Multi-View Eye Tracking

no code implementations15 Nov 2017 Nuri Murat Arar, Jean-Philippe Thiran

Despite significant advances in improving the gaze tracking accuracy under controlled conditions, the tracking robustness under real-world conditions, such as large head pose and movements, use of eyeglasses, illumination and eye type variations, remains a major challenge in eye tracking.

Visual Speech Recognition Using PCA Networks and LSTMs in a Tandem GMM-HMM System

no code implementations19 Oct 2017 Marina Zimmermann, Mostafa Mehdipour Ghazi, Hazim Kemal Ekenel, Jean-Philippe Thiran

Automatic visual speech recognition is an interesting problem in pattern recognition especially when audio data is noisy or not readily available.

Sentence speech-recognition +1

Combining Multiple Views for Visual Speech Recognition

no code implementations19 Oct 2017 Marina Zimmermann, Mostafa Mehdipour Ghazi, Hazim Kemal Ekenel, Jean-Philippe Thiran

In this paper, we explore this aspect and provide a comprehensive study on combining multiple views for visual speech recognition.

Sentence speech-recognition +1

Combining LiDAR Space Clustering and Convolutional Neural Networks for Pedestrian Detection

no code implementations17 Oct 2017 Damien Matti, Hazim Kemal Ekenel, Jean-Philippe Thiran

In purely image-based pedestrian detection approaches, the state-of-the-art results have been achieved with convolutional neural networks (CNN) and surprisingly few detection frameworks have been built upon multi-cue approaches.

Clustering Pedestrian Detection

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