5 papers
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…
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:…
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,…
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…
ViLU: Learning Vision-Language Uncertainties for Failure Prediction
Marc Lafon, Yannis Karmim, Julio Silva-RodrÃguez +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…