10 papers
The Gap Is in the Geometry: A Convergent Meta-Analysis of Multi-Facet Aerial and Remote Sensing Video Understanding
Georgios Angelidis, Aggelos Psiris, Maria Vakalopoulou +3
Aerial and remote sensing video is increasingly evaluated like web video, by posing multiple-choice questions to multimodal large language models (MLLMs) over sampled frames and re…
CalCErt: Bin-wise Certification of Confidence Calibration in Medical Image Classification
Leo Fillioux, Stergios Christodoulidis, Maria Vakalopoulou +1
Deep neural networks remain vulnerable to adversarial perturbations, which can distort not only predictions but also confidence scores, undermining uncertainty calibration. While e…
FOCUS: Benchmarking Retinal Model Generalization from Foundation Vision Encoders to Multimodal LLMs
David Restrepo, Chenwei Wu, Luis Filipe Nakayama +4
Progress in AI-based retinal image analysis has accelerated with the adoption of foundation models, yet evaluating their real-world reliability remains challenging. Performance rep…
CAR-MIL: Counterfactual Attention Regularization for Multiple Instance Learning
Imane Chraki, Pierre Marza, Stergios Christodoulidis +1
Multiple Instance Learning (MIL) is widely used for weakly supervised learning, particularly in digital pathology, where fine-grained annotations are costly. Most MIL methods aggre…
Medical Context Distorts Decisions in Clinical Vision Language Models
David Restrepo, Ira Ktena, Maria Vakalopoulou +2
Vision-language models (VLMs) are increasingly proposed for clinical decision support, yet their reliability in real-world scenarios that require integrating both visual and textua…
On the Cone Effect and Modality Gap in Medical Vision-Language Embeddings
David Restrepo, Miguel L Martins, Chenwei Wu +5
Vision-Language Models (VLMs) exhibit a characteristic "cone effect" in which nonlinear encoders map embeddings into highly concentrated regions of the representation space, contri…
GATE-AD: Graph Attention Network Encoding For Few-Shot Industrial Visual Anomaly Detection
Aggelos Psiris, Yannis Panagakis, Maria Vakalopoulou +1
Few-Shot Industrial Visual Anomaly Detection (FS-IVAD) is a critical task in modern manufacturing, where automated product inspection systems must identify rare defects using only…
Information Maximization for Long-Tailed Semi-Supervised Domain Generalization
Leo Fillioux, Omprakash Chakraborty, Quentin Gopée +6
Semi-supervised domain generalization (SSDG) has recently emerged as an appealing alternative to tackle domain generalization when labeled data is scarce but unlabeled samples acro…
CDG-MAE: Cross-view Masked Modeling using Diffusion Generated Views
Varun Belagali, Pierre Marza, Srikar Yellapragada +7
Cross-view masked autoencoding has emerged as a powerful pretext task for learning dense correspondences, which are essential for applications such as video label propagation. The…
You Don't Need Domain-Specific Data Augmentations When Scaling Self-Supervised Learning
Théo Moutakanni, Maxime Oquab, Marc Szafraniec +2
Self-Supervised learning (SSL) with Joint-Embedding Architectures (JEA) has led to outstanding performances. All instantiations of this paradigm were trained using strong and well-…