# Dual Memory Networks: A Versatile Adaptation Approach for Vision-Language Models

arXiv: https://arxiv.org/abs/2403.17589 · HTML: https://mlsanity.com/paper/2403.17589/

## Key facts

- Cited by 52 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 58 of its 78 references that are in the map.
- First posted on arXiv 26 Mar 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 58)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [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)
- [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)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [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)
- [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)
- [Robust fine-tuning of zero-shot models](https://mlsanity.com/paper/2109.01903/) (2021)
- [MaPLe: Multi-modal Prompt Learning](https://mlsanity.com/paper/2210.03117/) (2022)
- [PointCLIP: Point Cloud Understanding by CLIP](https://mlsanity.com/paper/2112.02413/) (2021)
- [Video Object Segmentation using Space-Time Memory Networks](https://mlsanity.com/paper/1904.00607/) (2019)
- [Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling](https://mlsanity.com/paper/2111.03930/) (2021)
- [Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models](https://mlsanity.com/paper/2209.07511/) (2022)
- [Memory Networks](https://mlsanity.com/paper/1410.3916/) (2014)
- [Prompt-aligned Gradient for Prompt Tuning](https://mlsanity.com/paper/2205.14865/) (2022)
- [Visual Classification via Description from Large Language Models](https://mlsanity.com/paper/2210.07183/) (2022)
- [SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution](https://mlsanity.com/paper/2311.16518/) (2023)
- [VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidance](https://mlsanity.com/paper/2204.08583/) (2022)
- [Self-regulating Prompts: Foundational Model Adaptation without Forgetting](https://mlsanity.com/paper/2307.06948/) (2023)

## Built on by (most cited first, 30 of 52)

- [Dual Prototype Evolving for Test-Time Generalization of Vision-Language Models](https://mlsanity.com/paper/2410.12790/) (2024)
- [AWT: Transferring Vision-Language Models via Augmentation, Weighting, and Transportation](https://mlsanity.com/paper/2407.04603/) (2024)
- [DOTA: Distributional Test-Time Adaptation of Vision-Language Models](https://mlsanity.com/paper/2409.19375/) (2024)
- [Advances in Multimodal Adaptation and Generalization: From Traditional Approaches to Foundation Models](https://mlsanity.com/paper/2501.18592/) (2025)
- [Historical Test-time Prompt Tuning for Vision Foundation Models](https://mlsanity.com/paper/2410.20346/) (2024)
- [LAPT: Label-driven Automated Prompt Tuning for OOD Detection with Vision-Language Models](https://mlsanity.com/paper/2407.08966/) (2024)
- [AdaNeg: Adaptive Negative Proxy Guided OOD Detection with Vision-Language Models](https://mlsanity.com/paper/2410.20149/) (2024)
- [ProKeR: A Kernel Perspective on Few-Shot Adaptation of Large Vision-Language Models](https://mlsanity.com/paper/2501.11175/) (2025)
- [Realistic Test-Time Adaptation of Vision-Language Models](https://mlsanity.com/paper/2501.03729/) (2025)
- [DG-PIC: Domain Generalized Point-In-Context Learning for Point Cloud Understanding](https://mlsanity.com/paper/2407.08801/) (2024)
- [COSMIC: Clique-Oriented Semantic Multi-space Integration for Robust CLIP Test-Time Adaptation](https://mlsanity.com/paper/2503.23388/) (2025)
- [Dynamic Multimodal Prototype Learning in Vision-Language Models](https://mlsanity.com/paper/2507.03657/) (2025)
- [Latte: Collaborative Test-Time Adaptation of Vision-Language Models in Federated Learning](https://mlsanity.com/paper/2507.21494/) (2025)
- [Efficient and Context-Aware Label Propagation for Zero-/Few-Shot Training-Free Adaptation of Vision-Language Model](https://mlsanity.com/paper/2412.18303/) (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)
- [Black Sheep in the Herd: Playing with Spuriously Correlated Attributes for Vision-Language Recognition](https://mlsanity.com/paper/2502.15809/) (2025)
- [Generalizing vision-language models to novel domains: A comprehensive survey](https://mlsanity.com/paper/2506.18504/) (2025)
- [Bidirectional Prototype-Reward co-Evolution for Test-Time Adaptation of Vision-Language Models](https://mlsanity.com/paper/2503.09394/) (2025)
- [Multi-Cache Enhanced Prototype Learning for Test-Time Generalization of Vision-Language Models](https://mlsanity.com/paper/2508.01225/) (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)
- [Mint: A Simple Test-Time Adaptation of Vision-Language Models against Common Corruptions](https://mlsanity.com/paper/2510.22127/) (2025)
- [Context-Aware Multimodal Pretraining](https://mlsanity.com/paper/2411.15099/) (2024)
- [TEST-V: TEst-time Support-set Tuning for Zero-shot Video Classification](https://mlsanity.com/paper/2502.00426/) (2025)
- [To Trust Or Not To Trust Your Vision-Language Model's Prediction](https://mlsanity.com/paper/2505.23745/) (2025)
- [ETTA: Efficient Test-Time Adaptation for Vision-Language Models through Dynamic Embedding Updates](https://mlsanity.com/paper/2508.05898/) (2025)
- [Test-Time Spectrum-Aware Latent Steering for Zero-Shot Generalization in Vision-Language Models](https://mlsanity.com/paper/2511.09809/) (2025)
- [What Drives Test-Time Adaptation for CLIP? A Controlled Empirical Study from an Update Perspective](https://mlsanity.com/paper/2606.14299/) (2026)
- [Diversity Covariance-Aware Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2503.01531/) (2025)

## Abstract (arXiv)

With the emergence of pre-trained vision-language models like CLIP, how to adapt them to various downstream classification tasks has garnered significant attention in recent research. The adaptation strategies can be typically categorized into three paradigms: zero-shot adaptation, few-shot adaptation, and the recently-proposed training-free few-shot adaptation. Most existing approaches are tailored for a specific setting and can only cater to one or two of these paradigms. In this paper, we introduce a versatile adaptation approach that can effectively work under all three settings. Specifically, we propose the dual memory networks that comprise dynamic and static memory components. The static memory caches training data knowledge, enabling training-free few-shot adaptation, while the dynamic memory preserves historical test features online during the testing process, allowing for the exploration of additional data insights beyond the training set. This novel capability enhances model performance in the few-shot setting and enables model usability in the absence of training data. The two memory networks employ the same flexible memory interactive strategy, which can operate in a training-free mode and can be further enhanced by incorporating learnable projection layers. Our approach is tested across 11 datasets under the three task settings. Remarkably, in the zero-shot scenario, it outperforms existing methods by over 3% and even shows superior results against methods utilizing external training data. Additionally, our method exhibits robust performance against natural distribution shifts. Codes are available at urlhttps://github.com/YBZh/DMN.