2 papers
cs.CV2026
PrAda: Few-Shot Visual Adaptation for Text-Prompted Segmentation
Gabriele Rosi, Fabio Cermelli, Carlo Masone +1
Segmenting images is critical for visual understanding but demands extensive pixel-level annotations. Foundational models have enabled new paradigms for predicting new classes guid…
cs.CV2025
Show or Tell? A Benchmark To Evaluate Visual and Textual Prompts in Semantic Segmentation
Gabriele Rosi, Fabio Cermelli
Prompt engineering has shown remarkable success with large language models, yet its systematic exploration in computer vision remains limited. In semantic segmentation, both textua…