From open-vocabulary to vocabulary-free semantic segmentation

Download PDF
Open Webpage

Klara Reichard, Giulia Rizzoli, Stefano Gasperini, Lukas Hoyer, Pietro Zanuttigh, Nassir Navab, Federico Tombari

Published: 2025, Last Modified: 09 Nov 2025Pattern Recognit. Lett. 2025EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Highlights•Propose a novel two-stage pipeline using an image tagger and a class-specific decoder.•Setting a new benchmark for Vocabulary-Free Semantic Segmentation.•Show the impact of enriched text inputs on the encoder assuming a perfect tagger.•Analyze the influence of undetected objects and false detections on the segmentation.