# On the test-time zero-shot generalization of vision-language models: Do we really need prompt learning?

arXiv: https://arxiv.org/abs/2405.02266 · HTML: https://mlsanity.com/paper/2405.02266/

## Key facts

- Cited by 67 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 43 of its 68 references that are in the map.
- First posted on arXiv 3 May 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, 30 of 43)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [Describing Textures in the Wild](https://mlsanity.com/paper/1311.3618/) (2013)
- [The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization](https://mlsanity.com/paper/2006.16241/) (2020)
- [Fine-Grained Visual Classification of Aircraft](https://mlsanity.com/paper/1306.5151/) (2013)
- [EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification](https://mlsanity.com/paper/1709.00029/) (2017)
- [Conditional Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2203.05557/) (2022)
- [Natural Adversarial Examples](https://mlsanity.com/paper/1907.07174/) (2019)
- [Grounded Language-Image Pre-training](https://mlsanity.com/paper/2112.03857/) (2021)
- [CLIP-Adapter: Better Vision-Language Models with Feature Adapters](https://mlsanity.com/paper/2110.04544/) (2021)
- [Learning Robust Global Representations by Penalizing Local Predictive Power](https://mlsanity.com/paper/1905.13549/) (2019)
- [How Can We Know What Language Models Know?](https://mlsanity.com/paper/1911.12543/) (2019)
- [Vision-Language Models for Vision Tasks: A Survey](https://mlsanity.com/paper/2304.00685/) (2023)
- [Robust fine-tuning of zero-shot models](https://mlsanity.com/paper/2109.01903/) (2021)
- [FILIP: Fine-grained Interactive Language-Image Pre-Training](https://mlsanity.com/paper/2111.07783/) (2021)
- [LiT: Zero-Shot Transfer with Locked-image text Tuning](https://mlsanity.com/paper/2111.07991/) (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)
- [Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classification](https://mlsanity.com/paper/2207.09519/) (2022)
- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [Prompt-aligned Gradient for Prompt Tuning](https://mlsanity.com/paper/2205.14865/) (2022)
- [Visual-Language Prompt Tuning with Knowledge-guided Context Optimization](https://mlsanity.com/paper/2303.13283/) (2023)
- [Factual Probing Is [MASK]: Learning vs. Learning to Recall](https://mlsanity.com/paper/2104.05240/) (2021)
- [What does a platypus look like? Generating customized prompts for zero-shot image classification](https://mlsanity.com/paper/2209.03320/) (2022)

## Built on by (most cited first, 30 of 67)

- [Low-Rank Few-Shot Adaptation of Vision-Language Models](https://mlsanity.com/paper/2405.18541/) (2024)
- [Dual Prototype Evolving for Test-Time Generalization of Vision-Language Models](https://mlsanity.com/paper/2410.12790/) (2024)
- [Frustratingly Easy Test-Time Adaptation of Vision-Language Models](https://mlsanity.com/paper/2405.18330/) (2024)
- [Boosting Vision-Language Models with Transduction](https://mlsanity.com/paper/2406.01837/) (2024)
- [R-TPT: Improving Adversarial Robustness of Vision-Language Models through Test-Time Prompt Tuning](https://mlsanity.com/paper/2504.11195/) (2025)
- [TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models](https://mlsanity.com/paper/2411.13136/) (2024)
- [Advances in Multimodal Adaptation and Generalization: From Traditional Approaches to Foundation Models](https://mlsanity.com/paper/2501.18592/) (2025)
- [Bayesian Test-Time Adaptation for Vision-Language Models](https://mlsanity.com/paper/2503.09248/) (2025)
- [A Survey on Efficient Vision-Language Models](https://mlsanity.com/paper/2504.09724/) (2025)
- [Realistic Test-Time Adaptation of Vision-Language Models](https://mlsanity.com/paper/2501.03729/) (2025)
- [SCAP: Transductive Test-Time Adaptation via Supportive Clique-based Attribute Prompting](https://mlsanity.com/paper/2503.12866/) (2025)
- [Enhancing Remote Sensing Vision-Language Models for Zero-Shot Scene Classification](https://mlsanity.com/paper/2409.00698/) (2024)
- [Boosting Vision-Language Models for Histopathology Classification: Predict all at once](https://mlsanity.com/paper/2409.01883/) (2024)
- [Free on the Fly: Enhancing Flexibility in Test-Time Adaptation with Online EM](https://mlsanity.com/paper/2507.06973/) (2025)
- [Online Gaussian Test-Time Adaptation of Vision-Language Models](https://mlsanity.com/paper/2501.04352/) (2025)
- [LoRA-TTT: Low-Rank Test-Time Training for Vision-Language Models](https://mlsanity.com/paper/2502.02069/) (2025)
- [Test-Time Visual In-Context Tuning](https://mlsanity.com/paper/2503.21777/) (2025)
- [Generalizing vision-language models to novel domains: A comprehensive survey](https://mlsanity.com/paper/2506.18504/) (2025)
- [Noise is an Efficient Learner for Zero-Shot Vision-Language Models](https://mlsanity.com/paper/2502.06019/) (2025)
- [Backpropagation-Free Test-Time Adaptation via Probabilistic Gaussian Alignment](https://mlsanity.com/paper/2508.15568/) (2025)
- [On the Element-Wise Representation and Reasoning in Zero-Shot Image Recognition: A Systematic Survey](https://mlsanity.com/paper/2408.04879/) (2024)
- [Evaluating and Improving Robustness in Large Language Models: A Survey and Future Directions](https://mlsanity.com/paper/2506.11111/) (2025)
- [Is Less More? Exploring Token Condensation as Training-free Test-time Adaptation](https://mlsanity.com/paper/2410.14729/) (2024)
- [Point-Cache: Test-time Dynamic and Hierarchical Cache for Robust and Generalizable Point Cloud Analysis](https://mlsanity.com/paper/2503.12150/) (2025)
- [ETTA: Efficient Test-Time Adaptation for Vision-Language Models through Dynamic Embedding Updates](https://mlsanity.com/paper/2508.05898/) (2025)
- [Self-Calibrated Consistency can Fight Back for Adversarial Robustness in Vision-Language Models](https://mlsanity.com/paper/2510.22785/) (2025)
- [What Drives Test-Time Adaptation for CLIP? A Controlled Empirical Study from an Update Perspective](https://mlsanity.com/paper/2606.14299/) (2026)
- [Space Rotation with Basis Transformation for Training-free Test-Time Adaptation](https://mlsanity.com/paper/2502.19946/) (2025)
- [VTD-CLIP: Video-to-Text Discretization via Prompting CLIP](https://mlsanity.com/paper/2503.18407/) (2025)
- [One Last Attention for Your Vision-Language Model](https://mlsanity.com/paper/2507.15480/) (2025)

## Abstract (arXiv)

The development of large vision-language models, notably CLIP, has catalyzed research into effective adaptation techniques, with a particular focus on soft prompt tuning. Conjointly, test-time augmentation, which utilizes multiple augmented views of a single image to enhance zero-shot generalization, is emerging as a significant area of interest. This has predominantly directed research efforts toward test-time prompt tuning. In contrast, we introduce a robust MeanShift for Test-time Augmentation (MTA), which surpasses prompt-based methods without requiring this intensive training procedure. This positions MTA as an ideal solution for both standalone and API-based applications. Additionally, our method does not rely on ad hoc rules (e.g., confidence threshold) used in some previous test-time augmentation techniques to filter the augmented views. Instead, MTA incorporates a quality assessment variable for each view directly into its optimization process, termed as the inlierness score. This score is jointly optimized with a density mode seeking process, leading to an efficient training- and hyperparameter-free approach. We extensively benchmark our method on 15 datasets and demonstrate MTA's superiority and computational efficiency. Deployed easily as plug-and-play module on top of zero-shot models and state-of-the-art few-shot methods, MTA shows systematic and consistent improvements.