# Dual-Foundation Models for Unsupervised Domain Adaptation

arXiv: https://arxiv.org/abs/2605.03365 · HTML: https://mlsanity.com/paper/2605.03365/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 46 of its 57 references that are in the map.
- First posted on arXiv 5 May 2026.

## Builds on (most cited first, 30 of 46)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation](https://mlsanity.com/paper/1511.00561/) (2015)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [A Closer Look at Memorization in Deep Networks](https://mlsanity.com/paper/1706.05394/) (2017)
- [Playing for Data: Ground Truth from Computer Games](https://mlsanity.com/paper/1608.02192/) (2016)
- [ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/1811.12833/) (2018)
- [FDA: Fourier Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2004.05498/) (2020)
- [Continual Test-Time Domain Adaptation](https://mlsanity.com/paper/2203.13591/) (2022)
- [LangSplat: 3D Language Gaussian Splatting](https://mlsanity.com/paper/2312.16084/) (2023)
- [DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation](https://mlsanity.com/paper/2111.14887/) (2021)
- [Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2101.10979/) (2021)
- [Exploring Cross-Image Pixel Contrast for Semantic Segmentation](https://mlsanity.com/paper/2101.11939/) (2021)
- [DACS: Domain Adaptation via Cross-domain Mixed Sampling](https://mlsanity.com/paper/2007.08702/) (2020)
- [MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation](https://mlsanity.com/paper/2212.01322/) (2022)
- [DLOW: Domain Flow for Adaptation and Generalization](https://mlsanity.com/paper/1812.05418/) (2018)
- [HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentation](https://mlsanity.com/paper/2204.13132/) (2022)
- [Learning Texture Invariant Representation for Domain Adaptation of Semantic Segmentation](https://mlsanity.com/paper/2003.00867/) (2020)
- [SemanticFusion: Dense 3D Semantic Mapping with Convolutional Neural Networks](https://mlsanity.com/paper/1609.05130/) (2016)
- [Differential Treatment for Stuff and Things: A Simple Unsupervised Domain Adaptation Method for Semantic Segmentation](https://mlsanity.com/paper/2003.08040/) (2020)
- [Unsupervised Domain Adaptation in Semantic Segmentation: a Review](https://mlsanity.com/paper/2005.10876/) (2020)
- [PixMatch: Unsupervised Domain Adaptation via Pixelwise Consistency Training](https://mlsanity.com/paper/2105.08128/) (2021)
- [SEEDS: Superpixels Extracted via Energy-Driven Sampling](https://mlsanity.com/paper/1309.3848/) (2013)
- [PODA: Prompt-driven Zero-shot Domain Adaptation](https://mlsanity.com/paper/2212.03241/) (2022)
- [Pixel-Level Cycle Association: A New Perspective for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2011.00147/) (2020)
- [Domain Adaptive Semantic Segmentation Using Weak Labels](https://mlsanity.com/paper/2007.15176/) (2020)

## Abstract (arXiv)

Semantic segmentation provides pixel-level scene understanding essential for autonomous driving and fine-grained perception tasks. However, training segmentation models requires costly, labor-intensive annotations on real-world datasets. Unsupervised Domain Adaptation (UDA) addresses this by training models on labeled synthetic data and adapting them to unlabeled real images. While conceptually simple, adaptation is challenging due to the domain gap, i.e., differences in visual appearance and scene structure between synthetic and real data. Prior approaches bridge this gap through pixel-level mixing or feature-level contrastive learning. Yet, these techniques suffer from two major limitations: (1) reliance on high-confidence pseudo-labels restricts learning to a subset of the target domain, and (2) prototype-based contrastive methods initialize class prototypes from source-trained models, yielding biased and unstable anchors during adaptation. To address these issues, we propose a dual-foundation UDA framework that leverages two complementary foundation models. First, we employ the Segment Anything Model (SAM) with superpixel-guided prompting to enable learning from a broader range of target pixels beyond high-confidence predictions. Second, we incorporate DINOv3 to construct stable, domain-invariant class prototypes through its robust representation learning. Our method achieves consistent improvements of +1.3% and +1.4% mIoU over strong UDA baselines on GTA-to-Cityscapes and SYNTHIA-to-Cityscapes, respectively.