3 papers
cs.CV2025
Differentiable Hierarchical Visual Tokenization
Marius Aasan, Martine Hjelkrem-Tan, Nico Catalano +2
Vision Transformers rely on fixed patch tokens that ignore the spatial and semantic structure of images. In this work, we introduce an end-to-end differentiable tokenizer that adap…
cs.CV2025
MARS: a Multimodal Alignment and Ranking System for Few-Shot Segmentation
Nico Catalano, Stefano Samele, Paolo Pertino +1
Few Shot Segmentation aims to segment novel object classes given only a handful of labeled examples, enabling rapid adaptation with minimal supervision. Current literature cruciall…
cs.CV2024
Few Shot Semantic Segmentation: a review of methodologies, benchmarks, and open challenges
Nico Catalano, Matteo Matteucci
Semantic segmentation, vital for applications ranging from autonomous driving to robotics, faces significant challenges in domains where collecting large annotated datasets is diff…