# Combining inherent knowledge of vision-language models with unsupervised domain adaptation through strong-weak guidance

arXiv: https://arxiv.org/abs/2312.04066 · HTML: https://mlsanity.com/paper/2312.04066/

## Key facts

- Cited by 4 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 33 of its 40 references that are in the map.
- First posted on arXiv 7 Dec 2023.

## Placed in

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

## Builds on (most cited first, 30 of 33)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [Moment Matching for Multi-Source Domain Adaptation](https://mlsanity.com/paper/1812.01754/) (2018)
- [Deep Hashing Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1706.07522/) (2017)
- [A Comprehensive Survey on Transfer Learning](https://mlsanity.com/paper/1911.02685/) (2019)
- [LiT: Zero-Shot Transfer with Locked-image text Tuning](https://mlsanity.com/paper/2111.07991/) (2021)
- [VisDA: The Visual Domain Adaptation Challenge](https://mlsanity.com/paper/1710.06924/) (2017)
- [Contrastive Adaptation Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1901.00976/) (2019)
- [Revisiting Batch Normalization For Practical Domain Adaptation](https://mlsanity.com/paper/1603.04779/) (2016)
- [Contrastive Test-Time Adaptation](https://mlsanity.com/paper/2204.10377/) (2022)
- [Data Filtering Networks](https://mlsanity.com/paper/2309.17425/) (2023)
- [Combined Scaling for Zero-shot Transfer Learning](https://mlsanity.com/paper/2111.10050/) (2021)
- [Unsupervised Domain Adaptation via Structurally Regularized Deep Clustering](https://mlsanity.com/paper/2003.08607/) (2020)
- [CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2109.06165/) (2021)
- [Domain Adaptation via Prompt Learning](https://mlsanity.com/paper/2202.06687/) (2022)
- [Visual Prompt Tuning for Test-time Domain Adaptation](https://mlsanity.com/paper/2210.04831/) (2022)
- [A Review of Single-Source Deep Unsupervised Visual Domain Adaptation](https://mlsanity.com/paper/2009.00155/) (2020)
- [A Closer Look at Smoothness in Domain Adversarial Training](https://mlsanity.com/paper/2206.08213/) (2022)
- [TVT: Transferable Vision Transformer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2108.05988/) (2021)
- [SENTRY: Selective Entropy Optimization via Committee Consistency for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2012.11460/) (2020)
- [Cross-Domain Gradient Discrepancy Minimization for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2106.04151/) (2021)
- [A Broad Study of Pre-training for Domain Generalization and Adaptation](https://mlsanity.com/paper/2203.11819/) (2022)
- [AD-CLIP: Adapting Domains in Prompt Space Using CLIP](https://mlsanity.com/paper/2308.05659/) (2023)
- [Safe Self-Refinement for Transformer-based Domain Adaptation](https://mlsanity.com/paper/2204.07683/) (2022)
- [Patch-Mix Transformer for Unsupervised Domain Adaptation: A Game Perspective](https://mlsanity.com/paper/2303.13434/) (2023)
- [Multi-Prompt Alignment for Multi-Source Unsupervised Domain Adaptation](https://mlsanity.com/paper/2209.15210/) (2022)
- [The Unreasonable Effectiveness of Large Language-Vision Models for Source-free Video Domain Adaptation](https://mlsanity.com/paper/2308.09139/) (2023)

## Built on by (most cited first, 4 of 4)

- [CLIP-Powered Domain Generalization and Domain Adaptation: A Comprehensive Survey](https://mlsanity.com/paper/2504.14280/) (2025)
- [ViLAaD: Enhancing "Attracting and Dispersing'' Source-Free Domain Adaptation with Vision-and-Language Model](https://mlsanity.com/paper/2503.23529/) (2025)
- [Knowledge Distillation and Enhanced Subdomain Adaptation Using Graph Convolutional Network for Resource-Constrained Bearing Fault Diagnosis](https://mlsanity.com/paper/2501.07173/) (2025)
- [Feature-Space Planes Searcher: A Universal Domain Adaptation Framework for Interpretability and Computational Efficiency](https://mlsanity.com/paper/2508.18693/) (2025)

## Abstract (arXiv)

Unsupervised domain adaptation (UDA) tries to overcome the tedious work of labeling data by leveraging a labeled source dataset and transferring its knowledge to a similar but different target dataset. Meanwhile, current vision-language models exhibit remarkable zero-shot prediction capabilities. In this work, we combine knowledge gained through UDA with the inherent knowledge of vision-language models. We introduce a strong-weak guidance learning scheme that employs zero-shot predictions to help align the source and target dataset. For the strong guidance, we expand the source dataset with the most confident samples of the target dataset. Additionally, we employ a knowledge distillation loss as weak guidance. The strong guidance uses hard labels but is only applied to the most confident predictions from the target dataset. Conversely, the weak guidance is employed to the whole dataset but uses soft labels. The weak guidance is implemented as a knowledge distillation loss with (shifted) zero-shot predictions. We show that our method complements and benefits from prompt adaptation techniques for vision-language models. We conduct experiments and ablation studies on three benchmarks (OfficeHome, VisDA, and DomainNet), outperforming state-of-the-art methods. Our ablation studies further demonstrate the contributions of different components of our algorithm.