313 citations · 381 across the 13 of their papers we have counts for
14 papers
CLIPArTT: Adaptation of CLIP to New Domains at Test Time
Gustavo Adolfo Vargas Hakim, David Osowiechi, Mehrdad Noori +5
Pre-trained vision-language models (VLMs), exemplified by CLIP, demonstrate remarkable adaptability across zero-shot classification tasks without additional training. However, thei…
Transductive Zero-Shot and Few-Shot CLIP
Ségolène Martin, Yunshi Huang, Fereshteh Shakeri +2
Transductive inference has been widely investigated in few-shot image classification, but completely overlooked in the recent, fast growing literature on adapting vision-langage mo…
LP++: A Surprisingly Strong Linear Probe for Few-Shot CLIP
Yunshi Huang, Fereshteh Shakeri, Jose Dolz +3
In a recent, strongly emergent literature on few-shot CLIP adaptation, Linear Probe (LP) has been often reported as a weak baseline. This has motivated intensive research building…
Pay Attention to Your Neighbours: Training-Free Open-Vocabulary Semantic Segmentation
Sina Hajimiri, Ismail Ben Ayed, Jose Dolz
Despite the significant progress in deep learning for dense visual recognition problems, such as semantic segmentation, traditional methods are constrained by fixed class sets. Mea…
A Closer Look at the Few-Shot Adaptation of Large Vision-Language Models
Julio Silva-Rodríguez, Sina Hajimiri, Ismail Ben Ayed +1
Efficient transfer learning (ETL) is receiving increasing attention to adapt large pre-trained language-vision models on downstream tasks with a few labeled samples. While signific…
Bag of Tricks for Fully Test-Time Adaptation
Saypraseuth Mounsaveng, Florent Chiaroni, Malik Boudiaf +2
Fully Test-Time Adaptation (TTA), which aims at adapting models to data drifts, has recently attracted wide interest. Numerous tricks and techniques have been proposed to ensure ro…
ClusT3: Information Invariant Test-Time Training
Gustavo A. Vargas Hakim, David Osowiechi, Mehrdad Noori +3
Deep Learning models have shown remarkable performance in a broad range of vision tasks. However, they are often vulnerable against domain shifts at test-time. Test-time training (…
Prompting classes: Exploring the Power of Prompt Class Learning in Weakly Supervised Semantic Segmentation
Balamurali Murugesan, Rukhshanda Hussain, Rajarshi Bhattacharya +2
Recently, CLIP-based approaches have exhibited remarkable performance on generalization and few-shot learning tasks, fueled by the power of contrastive language-vision pre-training…
Open-Set Likelihood Maximization for Few-Shot Learning
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 a few labeled samples, while simultaneously de…
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…
A Strong Baseline for Generalized Few-Shot Semantic Segmentation
Sina Hajimiri, Malik Boudiaf, Ismail Ben Ayed +1
This paper introduces a generalized few-shot segmentation framework with a straightforward training process and an easy-to-optimize inference phase. In particular, we propose a sim…
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…
Annotation-efficient deep learning for automatic medical image segmentation
Shanshan Wang, Cheng Li, Rongpin Wang +12
Automatic medical image segmentation plays a critical role in scientific research and medical care. Existing high-performance deep learning methods typically rely on large training…
Constrained Deep Networks: Lagrangian Optimization via Log-Barrier Extensions
Hoel Kervadec, Jose Dolz, Jing Yuan +3
This study investigates imposing hard inequality constraints on the outputs of convolutional neural networks (CNN) during training. Several recent works showed that the theoretical…