Recently, test-time adaptation has attracted wide interest in the context of vision-language models for image classification. However, to the best of our knowledge, the problem is completely overlooked in dense prediction tasks such as Open-Vocabulary Semantic Segmentation (OVSS). In response, we propose a novel TTA method tailored to adapting VLMs for segmentation during test time. Unlike TTA methods for image classification, our Multi-Level and Multi-Prompt (MLMP) entropy minimization integrates features from intermediate vision-encoder layers and is performed with different text-prompt templates at both the global CLS token and local pixel-wise levels. Our approach could be used as plug-and-play for any segmentation network, does not require additional training data or labels, and remains effective even with a single test sample. Furthermore, we introduce a comprehensive OVSS TTA benchmark suite, which integrates a rigorous evaluation protocol, seven segmentation datasets, and 15 common corruptions, with a total of 82 distinct test scenarios, establishing a standardized and comprehensive testbed for future TTA research in open-vocabulary segmentation. Our experiments on this suite demonstrate that our segmentation-tailored method consistently delivers significant gains over direct adoption of TTA classification baselines.
View on arXiv@article{noori2025_2505.21844,
title={ Test-Time Adaptation of Vision-Language Models for Open-Vocabulary Semantic Segmentation },
author={ Mehrdad Noori and David Osowiechi and Gustavo Adolfo Vargas Hakim and Ali Bahri and Moslem Yazdanpanah and Sahar Dastani and Farzad Beizaee and Ismail Ben Ayed and Christian Desrosiers },
journal={arXiv preprint arXiv:2505.21844},
year={ 2025 }
}