# Bidirectional Domain Mixup for Domain Adaptive Semantic Segmentation

arXiv: https://arxiv.org/abs/2303.09779 · HTML: https://mlsanity.com/paper/2303.09779/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 44 references that are in the map.
- First posted on arXiv 17 Mar 2023.

## Builds on (most cited first, 30 of 37)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [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)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers](https://mlsanity.com/paper/2012.15840/) (2020)
- [LVIS: A Dataset for Large Vocabulary Instance Segmentation](https://mlsanity.com/paper/1908.03195/) (2019)
- [CyCADA: Cycle-Consistent Adversarial Domain Adaptation](https://mlsanity.com/paper/1711.03213/) (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)
- [Learning to Adapt Structured Output Space for Semantic Segmentation](https://mlsanity.com/paper/1802.10349/) (2018)
- [FDA: Fourier Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2004.05498/) (2020)
- [Bidirectional Learning for Domain Adaptation of Semantic Segmentation](https://mlsanity.com/paper/1904.10620/) (2019)
- [Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2101.10979/) (2021)
- [DACS: Domain Adaptation via Cross-domain Mixed Sampling](https://mlsanity.com/paper/2007.08702/) (2020)
- [Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels](https://mlsanity.com/paper/2203.03884/) (2022)
- [ClassMix: Segmentation-Based Data Augmentation for Semi-Supervised Learning](https://mlsanity.com/paper/2007.07936/) (2020)
- [DLOW: Domain Flow for Adaptation and Generalization](https://mlsanity.com/paper/1812.05418/) (2018)
- [Instance Adaptive Self-Training for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2008.12197/) (2020)
- [Image to Image Translation for Domain Adaptation](https://mlsanity.com/paper/1712.00479/) (2017)
- [Source-Free Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2103.16372/) (2021)
- [Self-supervised Augmentation Consistency for Adapting Semantic Segmentation](https://mlsanity.com/paper/2105.00097/) (2021)
- [Classes Matter: A Fine-grained Adversarial Approach to Cross-domain Semantic Segmentation](https://mlsanity.com/paper/2007.09222/) (2020)
- [CrDoCo: Pixel-level Domain Transfer with Cross-Domain Consistency](https://mlsanity.com/paper/2001.03182/) (2020)
- [Domain Adaptive Semantic Segmentation with Self-Supervised Depth Estimation](https://mlsanity.com/paper/2104.13613/) (2021)
- [Context-Aware Mixup for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2108.03557/) (2021)
- [Cars Can't Fly up in the Sky: Improving Urban-Scene Segmentation via Height-driven Attention Networks](https://mlsanity.com/paper/2003.05128/) (2020)
- [Label-Driven Reconstruction for Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/2003.04614/) (2020)
- [Class-Balanced Pixel-Level Self-Labeling for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2203.09744/) (2022)

## Built on by (most cited first, 8 of 8)

- [Unified Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2311.13254/) (2023)
- [CAFS: Class Adaptive Framework for Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2303.11606/) (2023)
- [Cross-Domain Semantic Segmentation on Inconsistent Taxonomy using VLMs](https://mlsanity.com/paper/2408.02261/) (2024)
- [UDA4Inst: Unsupervised Domain Adaptation for Instance Segmentation](https://mlsanity.com/paper/2405.09682/) (2024)
- [A Unified Data Augmentation Framework for Low-Resource Multi-Domain Dialogue Generation](https://mlsanity.com/paper/2406.09881/) (2024)
- [LangDA: Building Context-Awareness via Language for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2503.12780/) (2025)
- [OurDB: Ouroboric Domain Bridging for Multi-Target Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2403.11582/) (2024)
- [In defense of the two-stage framework for open-set domain adaptive semantic segmentation](https://mlsanity.com/paper/2601.01439/) (2026)

## Abstract (arXiv)

Mixup provides interpolated training samples and allows the model to obtain smoother decision boundaries for better generalization. The idea can be naturally applied to the domain adaptation task, where we can mix the source and target samples to obtain domain-mixed samples for better adaptation. However, the extension of the idea from classification to segmentation (i.e., structured output) is nontrivial. This paper systematically studies the impact of mixup under the domain adaptaive semantic segmentation task and presents a simple yet effective mixup strategy called Bidirectional Domain Mixup (BDM). In specific, we achieve domain mixup in two-step: cut and paste. Given the warm-up model trained from any adaptation techniques, we forward the source and target samples and perform a simple threshold-based cut out of the unconfident regions (cut). After then, we fill-in the dropped regions with the other domain region patches (paste). In doing so, we jointly consider class distribution, spatial structure, and pseudo label confidence. Based on our analysis, we found that BDM leaves domain transferable regions by cutting, balances the dataset-level class distribution while preserving natural scene context by pasting. We coupled our proposal with various state-of-the-art adaptation models and observe significant improvement consistently. We also provide extensive ablation experiments to empirically verify our main components of the framework. Visit our project page with the code at https://sites.google.com/view/bidirectional-domain-mixup