429 citations · 664 across the 34 of their papers we have counts for
35 papers
Test-Time Generalized Category Discovery
Shambhavi Mishra, Omprakash Chakraborty, Julio Silva-Rodriguez +3
Test-Time Adaptation (TTA) and Generalized Category Discovery (GCD) are traditionally treated as disjoint problems: the former adapts models to domain shift assuming all test class…
PRiSM: Prototype Regularization for Few-Shot VLMs
Ghassen Baklouti, Omprakash Chakraborty, Jose Dolz +1
Training-free few-shot adaptation methods have gained significant attention recently in the context of Vision-language Models (VLMs). Yet, current benchmarks rely on strong assumpt…
Quantile Adaptive Temperature Scaling for Confidence Calibration
Omprakash Chakraborty, Leo Fillioux, Ismail Ben Ayed +1
Deep neural networks often produce poorly calibrated confidence estimates, overstating their certainty even when predictions are incorrect. Temperature Scaling remains the most wid…
SoC: Semantic Orthogonal Calibration for Test-Time Prompt Tuning
Leo Fillioux, Omprakash Chakraborty, Ismail Ben Ayed +4
With the increasing adoption of vision-language models (VLMs) in critical decision-making systems such as healthcare or autonomous driving, the calibration of their uncertainty est…
Robust Calibration of Large Vision-Language Adapters
Balamurali Murugesan, Julio Silva-Rodriguez, Ismail Ben Ayed +1
This paper addresses the critical issue of miscalibration in CLIP-based model adaptation, particularly in the challenging scenario of out-of-distribution (OOD) samples, which has b…
FDS: Feedback-guided Domain Synthesis with Multi-Source Conditional Diffusion Models for Domain Generalization
Mehrdad Noori, Milad Cheraghalikhani, Ali Bahri +5
Domain Generalization techniques aim to enhance model robustness by simulating novel data distributions during training, typically through various augmentation or stylization strat…
WATT: Weight Average Test-Time Adaptation of CLIP
David Osowiechi, Mehrdad Noori, Gustavo Adolfo Vargas Hakim +7
Vision-Language Models (VLMs) such as CLIP have yielded unprecedented performance for zero-shot image classification, yet their generalization capability may still be seriously cha…
GeoMask3D: Geometrically Informed Mask Selection for Self-Supervised Point Cloud Learning in 3D
Ali Bahri, Moslem Yazdanpanah, Mehrdad Noori +6
We introduce a pioneering approach to self-supervised learning for point clouds, employing a geometrically informed mask selection strategy called GeoMask3D (GM3D) to boost the eff…
NC-TTT: A Noise Contrastive Approach for Test-Time Training
David Osowiechi, Gustavo A. Vargas Hakim, Mehrdad Noori +5
Despite their exceptional performance in vision tasks, deep learning models often struggle when faced with domain shifts during testing. Test-Time Training (TTT) methods have recen…
Class and Region-Adaptive Constraints for Network Calibration
Balamurali Murugesan, Julio Silva-Rodriguez, Ismail Ben Ayed +1
In this work, we present a novel approach to calibrate segmentation networks that considers the inherent challenges posed by different categories and object regions. In particular,…
Exploring the Transferability of a Foundation Model for Fundus Images: Application to Hypertensive Retinopathy
Julio Silva-Rodriguez, Jihed Chelbi, Waziha Kabir +4
Using deep learning models pre-trained on Imagenet is the traditional solution for medical image classification to deal with data scarcity. Nevertheless, relevant literature suppor…
A transductive few-shot learning approach for classification of digital histopathological slides from liver cancer
Aymen Sadraoui, Ségolène Martin, Eliott Barbot +4
This paper presents a new approach for classifying 2D histopathology patches using few-shot learning. The method is designed to tackle a significant challenge in histopathology, wh…
Aggregated f-average Neural Network applied to Few-Shot Class Incremental Learning
Mathieu Vu, Emilie Chouzenoux, Ismail Ben Ayed +1
Ensemble learning leverages multiple models (i.e., weak learners) on a common machine learning task to enhance prediction performance. Basic ensembling approaches average the weak…
A Foundation Language-Image Model of the Retina (FLAIR): Encoding Expert Knowledge in Text Supervision
Julio Silva-Rodríguez, Hadi Chakor, Riadh Kobbi +2
Foundation vision-language models are currently transforming computer vision, and are on the rise in medical imaging fueled by their very promising generalization capabilities. How…
Automatic Data Augmentation Learning using Bilevel Optimization for Histopathological Images
Saypraseuth Mounsaveng, Issam Laradji, David Vázquez +2
Training a deep learning model to classify histopathological images is challenging, because of the color and shape variability of the cells and tissues, and the reduced amount of a…
Towards Foundation Models and Few-Shot Parameter-Efficient Fine-Tuning for Volumetric Organ Segmentation
Julio Silva-Rodríguez, Jose Dolz, Ismail Ben Ayed
The recent popularity of foundation models and the pre-train-and-adapt paradigm, where a large-scale model is transferred to downstream tasks, is gaining attention for volumetric m…
TFS-ViT: Token-Level Feature Stylization for Domain Generalization
Mehrdad Noori, Milad Cheraghalikhani, Ali Bahri +4
Standard deep learning models such as convolutional neural networks (CNNs) lack the ability of generalizing to domains which have not been seen during training. This problem is mai…
Calibrating Segmentation Networks with Margin-based Label Smoothing
Balamurali Murugesan, Bingyuan Liu, Adrian Galdran +2
Despite the undeniable progress in visual recognition tasks fueled by deep neural networks, there exists recent evidence showing that these models are poorly calibrated, resulting…
TCAM: Temporal Class Activation Maps for Object Localization in Weakly-Labeled Unconstrained Videos
Soufiane Belharbi, Ismail Ben Ayed, Luke McCaffrey +1
Weakly supervised video object localization (WSVOL) allows locating object in videos using only global video tags such as object class. State-of-art methods rely on multiple indepe…
Simplex Clustering via sBeta with Applications to Online Adjustment of Black-Box Predictions
Florent Chiaroni, Malik Boudiaf, Amar Mitiche +1
We explore clustering the softmax predictions of deep neural networks and introduce a novel probabilistic clustering method, referred to as k-sBetas. In the general context of clus…
Model-Agnostic Few-Shot Open-Set Recognition
Malik Boudiaf, Etienne Bennequin, Myriam Tami +4
We tackle the Few-Shot Open-Set Recognition (FSOSR) problem, i.e. classifying instances among a set of classes for which we only have few labeled samples, while simultaneously dete…
Negative Evidence Matters in Interpretable Histology Image Classification
Soufiane Belharbi, Marco Pedersoli, Ismail Ben Ayed +2
Using only global image-class labels, weakly-supervised learning methods, such as class activation mapping, allow training CNNs to jointly classify an image, and locate regions of…
The Devil is in the Margin: Margin-based Label Smoothing for Network Calibration
Bingyuan Liu, Ismail Ben Ayed, Adrian Galdran +1
In spite of the dominant performances of deep neural networks, recent works have shown that they are poorly calibrated, resulting in over-confident predictions. Miscalibration can…
Segmentation with mixed supervision: Confidence maximization helps knowledge distillation
Bingyuan Liu, Christian Desrosiers, Ismail Ben Ayed +1
Despite achieving promising results in a breadth of medical image segmentation tasks, deep neural networks require large training datasets with pixel-wise annotations. Obtaining th…