LPOSS: Label Propagation Over Patches and Pixels for Open-vocabulary Semantic Segmentation

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Stojnić, Vladan, Kalantidis, Yannis, Matas, Jiří, Tolias, Giorgos
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911020838027264
author Stojnić, Vladan
Kalantidis, Yannis
Matas, Jiří
Tolias, Giorgos
author_facet Stojnić, Vladan
Kalantidis, Yannis
Matas, Jiří
Tolias, Giorgos
contents We propose a training-free method for open-vocabulary semantic segmentation using Vision-and-Language Models (VLMs). Our approach enhances the initial per-patch predictions of VLMs through label propagation, which jointly optimizes predictions by incorporating patch-to-patch relationships. Since VLMs are primarily optimized for cross-modal alignment and not for intra-modal similarity, we use a Vision Model (VM) that is observed to better capture these relationships. We address resolution limitations inherent to patch-based encoders by applying label propagation at the pixel level as a refinement step, significantly improving segmentation accuracy near class boundaries. Our method, called LPOSS+, performs inference over the entire image, avoiding window-based processing and thereby capturing contextual interactions across the full image. LPOSS+ achieves state-of-the-art performance among training-free methods, across a diverse set of datasets. Code: https://github.com/vladan-stojnic/LPOSS
format Preprint
id arxiv_https___arxiv_org_abs_2503_19777
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LPOSS: Label Propagation Over Patches and Pixels for Open-vocabulary Semantic Segmentation
Stojnić, Vladan
Kalantidis, Yannis
Matas, Jiří
Tolias, Giorgos
Computer Vision and Pattern Recognition
Machine Learning
We propose a training-free method for open-vocabulary semantic segmentation using Vision-and-Language Models (VLMs). Our approach enhances the initial per-patch predictions of VLMs through label propagation, which jointly optimizes predictions by incorporating patch-to-patch relationships. Since VLMs are primarily optimized for cross-modal alignment and not for intra-modal similarity, we use a Vision Model (VM) that is observed to better capture these relationships. We address resolution limitations inherent to patch-based encoders by applying label propagation at the pixel level as a refinement step, significantly improving segmentation accuracy near class boundaries. Our method, called LPOSS+, performs inference over the entire image, avoiding window-based processing and thereby capturing contextual interactions across the full image. LPOSS+ achieves state-of-the-art performance among training-free methods, across a diverse set of datasets. Code: https://github.com/vladan-stojnic/LPOSS
title LPOSS: Label Propagation Over Patches and Pixels for Open-vocabulary Semantic Segmentation
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2503.19777