527 citations · 2.3k across the 108 of their papers we have counts for
13 papers · 2 filters
NERVE: Neighbourhood & Entropy-guided Random-walk for training free open-Vocabulary sEgmentation
Kunal Mahatha, Jose Dolz, Christian Desrosiers
Despite recent advances in Open-Vocabulary Semantic Segmentation (OVSS), existing training-free methods face several limitations: use of computationally expensive affinity refineme…
SGPMIL: Sparse Gaussian Process Multiple Instance Learning
Andreas Lolos, Stergios Christodoulidis, Aris L. Moustakas +2
Multiple Instance Learning (MIL) offers a natural solution for settings where only coarse, bag-level labels are available, without having access to instance-level annotations. This…
THUNDER: Tile-level Histopathology image UNDERstanding benchmark
Pierre Marza, Leo Fillioux, Sofiène Boutaj +6
Progress in a research field can be hard to assess, in particular when many concurrent methods are proposed in a short period of time. This is the case in digital pathology, where…
ViLU: Learning Vision-Language Uncertainties for Failure Prediction
Marc Lafon, Yannis Karmim, Julio Silva-Rodríguez +6
Reliable Uncertainty Quantification (UQ) and failure prediction remain open challenges for Vision-Language Models (VLMs). We introduce ViLU, a new Vision-Language Uncertainty quant…
Trustworthy Few-Shot Transfer of Medical VLMs through Split Conformal Prediction
Julio Silva-Rodríguez, Ismail Ben Ayed, Jose Dolz
Medical vision-language models (VLMs) have demonstrated unprecedented transfer capabilities and are being increasingly adopted for data-efficient image classification. Despite its…
Few-Shot, Now for Real: Medical VLMs Adaptation without Balanced Sets or Validation
Julio Silva-Rodríguez, Fereshteh Shakeri, Houda Bahig +2
Vision-language models (VLMs) are gaining attention in medical image analysis. These are pre-trained on large, heterogeneous data sources, yielding rich and transferable representa…
Full Conformal Adaptation of Medical Vision-Language Models
Julio Silva-Rodríguez, Leo Fillioux, Paul-Henry Cournède +4
Vision-language models (VLMs) pre-trained at large scale have shown unprecedented transferability capabilities and are being progressively integrated into medical image analysis. A…
Conformal Prediction for Zero-Shot Models
Julio Silva-Rodríguez, Ismail Ben Ayed, Jose Dolz
Vision-language models pre-trained at large scale have shown unprecedented adaptability and generalization to downstream tasks. Although its discriminative potential has been widel…
DART: Leveraging Distance for Test Time Adaptation in Person Re-Identification
Rajarshi Bhattacharya, Shakeeb Murtaza, Christian Desrosiers +3
Person re-identification (ReID) models are known to suffer from camera bias, where learned representations cluster according to camera viewpoints rather than identity, leading to s…
A Reality Check of Vision-Language Pre-training in Radiology: Have We Progressed Using Text?
Julio Silva-Rodríguez, Jose Dolz, Ismail Ben Ayed
Vision-language pre-training has recently gained popularity as it allows learning rich feature representations using large-scale data sources. This paradigm has quickly made its wa…
Correcting Deviations from Normality: A Reformulated Diffusion Model for Multi-Class Unsupervised Anomaly Detection
Farzad Beizaee, Gregory A. Lodygensky, Christian Desrosiers +1
Recent advances in diffusion models have spurred research into their application for Reconstruction-based unsupervised anomaly detection. However, these methods may struggle with m…
MAD-AD: Masked Diffusion for Unsupervised Brain Anomaly Detection
Farzad Beizaee, Gregory Lodygensky, Christian Desrosiers +1
Unsupervised anomaly detection in brain images is crucial for identifying injuries and pathologies without access to labels. However, the accurate localization of anomalies in medi…
BayesAdapter: enhanced uncertainty estimation in CLIP few-shot adaptation
Pablo Morales-Álvarez, Stergios Christodoulidis, Maria Vakalopoulou +2
The emergence of large pre-trained vision-language models (VLMs) represents a paradigm shift in machine learning, with unprecedented results in a broad span of visual recognition t…