# WATT: Weight Average Test-Time Adaptation of CLIP

arXiv: https://arxiv.org/abs/2406.13875 · HTML: https://mlsanity.com/paper/2406.13875/

## Key facts

- Cited by 33 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 23 of its 33 references that are in the map.
- First posted on arXiv 19 Jun 2024.

## 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, 23 of 23)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Averaging Weights Leads to Wider Optima and Better Generalization](https://mlsanity.com/paper/1803.05407/) (2018)
- [Deep Hashing Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1706.07522/) (2017)
- [Deeper, Broader and Artier Domain Generalization](https://mlsanity.com/paper/1710.03077/) (2017)
- [Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs](https://mlsanity.com/paper/1802.10026/) (2018)
- [SWAD: Domain Generalization by Seeking Flat Minima](https://mlsanity.com/paper/2102.08604/) (2021)
- [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)
- [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)
- [Test-Time Training with Masked Autoencoders](https://mlsanity.com/paper/2209.07522/) (2022)
- [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)
- [Diverse Data Augmentation with Diffusions for Effective Test-time Prompt Tuning](https://mlsanity.com/paper/2308.06038/) (2023)
- [Efficient Test-Time Adaptation of Vision-Language Models](https://mlsanity.com/paper/2403.18293/) (2024)
- [TTTFlow: Unsupervised Test-Time Training with Normalizing Flow](https://mlsanity.com/paper/2210.11389/) (2022)
- [ClusT3: Information Invariant Test-Time Training](https://mlsanity.com/paper/2310.12345/) (2023)
- [Lookaround Optimizer: k steps around, 1 step average](https://mlsanity.com/paper/2306.07684/) (2023)
- [NC-TTT: A Noise Contrastive Approach for Test-Time Training](https://mlsanity.com/paper/2404.08392/) (2024)

## Built on by (most cited first, 30 of 33)

- [Advances in Multimodal Adaptation and Generalization: From Traditional Approaches to Foundation Models](https://mlsanity.com/paper/2501.18592/) (2025)
- [Ranked Entropy Minimization for Continual Test-Time Adaptation](https://mlsanity.com/paper/2505.16441/) (2025)
- [Realistic Test-Time Adaptation of Vision-Language Models](https://mlsanity.com/paper/2501.03729/) (2025)
- [textttBATCLIP: Bimodal Online Test-Time Adaptation for CLIP](https://mlsanity.com/paper/2412.02837/) (2024)
- [Test-Time Adaptation of Vision-Language Models for Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2505.21844/) (2025)
- [A Simple and Efficient Baseline for Zero-Shot Generative Classification](https://mlsanity.com/paper/2412.12594/) (2024)
- [LoRA-TTT: Low-Rank Test-Time Training for Vision-Language Models](https://mlsanity.com/paper/2502.02069/) (2025)
- [Generalizing vision-language models to novel domains: A comprehensive survey](https://mlsanity.com/paper/2506.18504/) (2025)
- [Mint: A Simple Test-Time Adaptation of Vision-Language Models against Common Corruptions](https://mlsanity.com/paper/2510.22127/) (2025)
- [Test-Time Adaptation via Cache Personalization for Facial Expression Recognition in Videos](https://mlsanity.com/paper/2603.21309/) (2026)
- [Test-time Correlation Alignment](https://mlsanity.com/paper/2505.00533/) (2025)
- [Histopath-C: Towards Realistic Domain Shifts for Histopathology Vision-Language Adaptation](https://mlsanity.com/paper/2601.12493/) (2026)
- [Semantic Anchor Transport: Robust Test-Time Adaptation for Vision-Language Models](https://mlsanity.com/paper/2411.17002/) (2024)
- [Processing and acquisition traces in visual encoders: What does CLIP know about your camera?](https://mlsanity.com/paper/2508.10637/) (2025)
- [Purge-Gate: Backpropagation-Free Test-Time Adaptation for Point Clouds Classification via Token Purging](https://mlsanity.com/paper/2509.09785/) (2025)
- [textttAVROBUSTBENCH: Benchmarking the Robustness of Audio-Visual Recognition Models at Test-Time](https://mlsanity.com/paper/2506.00358/) (2025)
- [CLIP-AUTT: Test-Time Personalization with Action Unit Prompting for Fine-Grained Video Emotion Recognition](https://mlsanity.com/paper/2603.27999/) (2026)
- [FRET: Feature Redundancy Elimination for Test Time Adaptation](https://mlsanity.com/paper/2505.10641/) (2025)
- [Uniformity First: Uniformity-aware Test-time Adaptation of Vision-language Models against Image Corruption](https://mlsanity.com/paper/2505.12912/) (2025)
- [Enhancing Monte Carlo Dropout Performance for Uncertainty Quantification](https://mlsanity.com/paper/2505.15671/) (2025)
- [Adapt-As-You-Walk Through the Clouds: Training-Free Online Test-Time Adaptation of 3D Vision-Language Foundation Models](https://mlsanity.com/paper/2511.15311/) (2025)
- [LQA: A Lightweight Quantized-Adaptive Framework for Vision-Language Models on the Edge](https://mlsanity.com/paper/2602.07849/) (2026)
- [ORION: ORthonormal Text Encoding for Universal VLM AdaptatION](https://mlsanity.com/paper/2602.19530/) (2026)
- [Multi-Hypothesis Test-Time Adaptation to Mitigate Underspecification](https://mlsanity.com/paper/2607.00259/) (2026)
- [Can Experts Adapt Without Training? On Test-Time Modality Generalization in MVLMs](https://mlsanity.com/paper/2607.16726/) (2026)
- [TransForSeg: A Multitask Stereo ViT for Joint Stereo Segmentation and 3D Force Estimation in Catheterization](https://mlsanity.com/paper/2509.01605/) (2025)
- [TRUST: Test-Time Refinement using Uncertainty-Guided SSM Traverses](https://mlsanity.com/paper/2509.22813/) (2025)
- [Ramen: Robust Test-Time Adaptation of Vision-Language Models with Active Sample Selection](https://mlsanity.com/paper/2604.21728/) (2026)
- [SHED: Style-Homogenized Embedding Alignment for Domain Generalization](https://mlsanity.com/paper/2605.16973/) (2026)
- [Test-Time Adaptation via Dual Distillation for Videos Under Severe Distribution Shifts](https://mlsanity.com/paper/2607.24611/) (2026)

## Abstract (arXiv)

Vision-Language Models (VLMs) such as CLIP have yielded unprecedented performance for zero-shot image classification, yet their generalization capability may still be seriously challenged when confronted to domain shifts. In response, we present Weight Average Test-Time Adaptation (WATT) of CLIP, a pioneering approach facilitating full test-time adaptation (TTA) of this VLM. Our method employs a diverse set of templates for text prompts, augmenting the existing framework of CLIP. Predictions are utilized as pseudo labels for model updates, followed by weight averaging to consolidate the learned information globally. Furthermore, we introduce a text ensemble strategy, enhancing overall test performance by aggregating diverse textual cues. Our findings underscore the efficacy of WATT in enhancing performance across diverse datasets, including CIFAR-10-C, CIFAR-10.1, CIFAR-100-C, VisDA-C, and several other challenging datasets, effectively covering a wide range of domain shifts. Notably, these enhancements are achieved without necessitating additional model transformations or trainable modules. Moreover, compared to other Test-Time Adaptation methods, our approach can operate effectively with just a single image. Highlighting the potential of innovative test-time strategies, this research emphasizes their role in fortifying the adaptability of VLMs. The implementation is available at: urlhttps://github.com/Mehrdad-Noori/WATT.git.