# Test-Time Adaptation of Vision-Language Models for Open-Vocabulary Semantic Segmentation

arXiv: https://arxiv.org/abs/2505.21844 · HTML: https://mlsanity.com/paper/2505.21844/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in Prompt learning and adaptation of CLIP, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 35 of its 47 references that are in the map.
- First posted on arXiv 28 May 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Prompt learning and adaptation of CLIP](https://mlsanity.com/mllm/prompt-learning-and-adaptation-of-clip/)

## Builds on (most cited first, 30 of 35)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [COCO-Stuff: Thing and Stuff Classes in Context](https://mlsanity.com/paper/1612.03716/) (2016)
- [Playing for Data: Ground Truth from Computer Games](https://mlsanity.com/paper/1608.02192/) (2016)
- [Extract Free Dense Labels from CLIP](https://mlsanity.com/paper/2112.01071/) (2021)
- [Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP](https://mlsanity.com/paper/2210.04150/) (2022)
- [GroupViT: Semantic Segmentation Emerges from Text Supervision](https://mlsanity.com/paper/2202.11094/) (2022)
- [Scaling Open-Vocabulary Image Segmentation with Image-Level Labels](https://mlsanity.com/paper/2112.12143/) (2021)
- [PANet: Few-Shot Image Semantic Segmentation with Prototype Alignment](https://mlsanity.com/paper/1908.06391/) (2019)
- [Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models](https://mlsanity.com/paper/2209.07511/) (2022)
- [MEMO: Test Time Robustness via Adaptation and Augmentation](https://mlsanity.com/paper/2110.09506/) (2021)
- [AudioCLIP: Extending CLIP to Image, Text and Audio](https://mlsanity.com/paper/2106.13043/) (2021)
- [Long-CLIP: Unlocking the Long-Text Capability of CLIP](https://mlsanity.com/paper/2403.15378/) (2024)
- [Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shift](https://mlsanity.com/paper/2006.10963/) (2020)
- [CLIP-Driven Universal Model for Organ Segmentation and Tumor Detection](https://mlsanity.com/paper/2301.00785/) (2023)
- [Parameter-free Online Test-time Adaptation](https://mlsanity.com/paper/2201.05718/) (2022)
- [Frozen CLIP Models are Efficient Video Learners](https://mlsanity.com/paper/2208.03550/) (2022)
- [SCLIP: Rethinking Self-Attention for Dense Vision-Language Inference](https://mlsanity.com/paper/2312.01597/) (2023)
- [Source-Free Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2103.16372/) (2021)
- [Learning to Generate Text-grounded Mask for Open-world Semantic Segmentation from Only Image-Text Pairs](https://mlsanity.com/paper/2212.00785/) (2022)
- [Grounding Everything: Emerging Localization Properties in Vision-Language Transformers](https://mlsanity.com/paper/2312.00878/) (2023)
- [Pay Attention to Your Neighbours: Training-Free Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2404.08181/) (2024)
- [On Pitfalls of Test-Time Adaptation](https://mlsanity.com/paper/2306.03536/) (2023)
- [TTTFlow: Unsupervised Test-Time Training with Normalizing Flow](https://mlsanity.com/paper/2210.11389/) (2022)
- [WATT: Weight Average Test-Time Adaptation of CLIP](https://mlsanity.com/paper/2406.13875/) (2024)
- [ClusT3: Information Invariant Test-Time Training](https://mlsanity.com/paper/2310.12345/) (2023)

## Built on by (most cited first, 10 of 10)

- [Histopath-C: Towards Realistic Domain Shifts for Histopathology Vision-Language Adaptation](https://mlsanity.com/paper/2601.12493/) (2026)
- [Purge-Gate: Backpropagation-Free Test-Time Adaptation for Point Clouds Classification via Token Purging](https://mlsanity.com/paper/2509.09785/) (2025)
- [StructXLIP: Enhancing Vision-language Models with Multimodal Structural Cues](https://mlsanity.com/paper/2602.20089/) (2026)
- [Test-Time Prototype Adaptation for Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2608.08290/) (2026)
- [TRUST: Test-Time Refinement using Uncertainty-Guided SSM Traverses](https://mlsanity.com/paper/2509.22813/) (2025)
- [Retrieve and Segment: Are a Few Examples Enough to Bridge the Supervision Gap in Open-Vocabulary Segmentation?](https://mlsanity.com/paper/2602.23339/) (2026)
- [IGLOSS: Image Generation for Lidar Open-vocabulary Semantic Segmentation](https://mlsanity.com/paper/2604.01361/) (2026)
- [Self-Improving is Often Sudden: Enlightenment-style Finetuning for Large-Scale Models](https://mlsanity.com/paper/2607.13395/) (2026)
- [Towards Continual Test-Time Adaptation of Vision-Language Models in Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2608.29923/) (2026)
- [Position Aware Layer Queries for Test Time Training in Vision Language Models](https://mlsanity.com/paper/2609.34021/) (2026)

## Abstract (arXiv)

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, nine segmentation datasets, 15 common synthetic corruptions, and additional real and rendered domain shifts, with a total of 87 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. Code and data are available at https://github.com/dosowiechi/MLMP.