collaborators

5 papers

cs.CV2026

JAFAR: Jack up Any Feature at Any Resolution

Paul Couairon, Loick Chambon, Louis Serrano +3

Foundation Vision Encoders have become essential for a wide range of dense vision tasks. However, their low-resolution spatial feature outputs necessitate feature upsampling to pro…

cs.CV2025

NAF: Zero-Shot Feature Upsampling via Neighborhood Attention Filtering

Loick Chambon, Paul Couairon, Eloi Zablocki +3

Vision Foundation Models (VFMs) extract spatially downsampled representations, posing challenges for pixel-level tasks. Existing upsampling approaches face a fundamental trade-off:…

cs.CV2025

FreeSeg-Diff: Training-Free Open-Vocabulary Segmentation with Diffusion Models

Barbara Toniella Corradini, Mustafa Shukor, Paul Couairon +3

Foundation models have exhibited unprecedented capabilities in tackling many domains and tasks. Models such as CLIP are currently widely used to bridge cross-modal representations,…

cs.CV2025

DiffCut: Catalyzing Zero-Shot Semantic Segmentation with Diffusion Features and Recursive Normalized Cut

Paul Couairon, Mustafa Shukor, Jean-Emmanuel Haugeard +2

Foundation models have emerged as powerful tools across various domains including language, vision, and multimodal tasks. While prior works have addressed unsupervised image segmen…

cs.CV2025

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…