# Bi-Directional Generation for Unsupervised Domain Adaptation

arXiv: https://arxiv.org/abs/2002.04869 · HTML: https://mlsanity.com/paper/2002.04869/

## Key facts

- Cited by 26 papers in the map (data through 7 Oct 2026).
- First posted on arXiv 12 Feb 2020.

## Built on by (most cited first, 26 of 26)

- [Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptation](https://mlsanity.com/paper/2110.04202/) (2021)
- [Generalized Source-free Domain Adaptation](https://mlsanity.com/paper/2108.01614/) (2021)
- [Source-free Domain Adaptation via Avatar Prototype Generation and Adaptation](https://mlsanity.com/paper/2106.15326/) (2021)
- [Divide and Contrast: Source-free Domain Adaptation via Adaptive Contrastive Learning](https://mlsanity.com/paper/2211.06612/) (2022)
- [When Source-Free Domain Adaptation Meets Learning with Noisy Labels](https://mlsanity.com/paper/2301.13381/) (2023)
- [ProxyMix: Proxy-based Mixup Training with Label Refinery for Source-Free Domain Adaptation](https://mlsanity.com/paper/2205.14566/) (2022)
- [Transformer-Based Source-Free Domain Adaptation](https://mlsanity.com/paper/2105.14138/) (2021)
- [Generation, augmentation, and alignment: A pseudo-source domain based method for source-free domain adaptation](https://mlsanity.com/paper/2109.04015/) (2021)
- [Variational Model Perturbation for Source-Free Domain Adaptation](https://mlsanity.com/paper/2210.10378/) (2022)
- [Nearest Neighborhood-Based Deep Clustering for Source Data-absent Unsupervised Domain Adaptation](https://mlsanity.com/paper/2107.12585/) (2021)
- [Towards Novel Target Discovery Through Open-Set Domain Adaptation](https://mlsanity.com/paper/2105.02432/) (2021)
- [VQ-Flows: Vector Quantized Local Normalizing Flows](https://mlsanity.com/paper/2203.11556/) (2022)
- [Trust your Good Friends: Source-free Domain Adaptation by Reciprocal Neighborhood Clustering](https://mlsanity.com/paper/2309.00528/) (2023)
- [Domain-Guided Conditional Diffusion Model for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2309.14360/) (2023)
- [Graphical Modeling for Multi-Source Domain Adaptation](https://mlsanity.com/paper/2104.13057/) (2021)
- [Boost Test-Time Performance with Closed-Loop Inference](https://mlsanity.com/paper/2203.10853/) (2022)
- [GearNet: Stepwise Dual Learning for Weakly Supervised Domain Adaptation](https://mlsanity.com/paper/2201.06001/) (2022)
- [Unsupervised Reinforcement Adaptation for Class-Imbalanced Text Classification](https://mlsanity.com/paper/2205.13139/) (2022)
- [Exploiting Domain Transferability for Collaborative Inter-level Domain Adaptive Object Detection](https://mlsanity.com/paper/2207.09613/) (2022)
- [Open-Set Multi-Source Multi-Target Domain Adaptation](https://mlsanity.com/paper/2302.00995/) (2023)
- [AMA-SAM: Adversarial Multi-Domain Alignment of Segment Anything Model for High-Fidelity Histology Nuclei Segmentation](https://mlsanity.com/paper/2503.21695/) (2025)
- [Diffusion-based Target Sampler for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2303.12724/) (2023)
- [DomainInv: Domain Invariant Fine Tuning and Adversarial Label Correction For QA Domain Adaptation](https://mlsanity.com/paper/2305.05589/) (2023)
- [Imbalance-Agnostic Source-Free Domain Adaptation via Avatar Prototype Alignment](https://mlsanity.com/paper/2305.12649/) (2023)
- [SIDE: Self-supervised Intermediate Domain Exploration for Source-free Domain Adaptation](https://mlsanity.com/paper/2310.08928/) (2023)
- [Energy-Based Pseudo-Label Refining for Source-free Domain Adaptation](https://mlsanity.com/paper/2504.16692/) (2025)

## Abstract (arXiv)

Unsupervised domain adaptation facilitates the unlabeled target domain relying on well-established source domain information. The conventional methods forcefully reducing the domain discrepancy in the latent space will result in the destruction of intrinsic data structure. To balance the mitigation of domain gap and the preservation of the inherent structure, we propose a Bi-Directional Generation domain adaptation model with consistent classifiers interpolating two intermediate domains to bridge source and target domains. Specifically, two cross-domain generators are employed to synthesize one domain conditioned on the other. The performance of our proposed method can be further enhanced by the consistent classifiers and the cross-domain alignment constraints. We also design two classifiers which are jointly optimized to maximize the consistency on target sample prediction. Extensive experiments verify that our proposed model outperforms the state-of-the-art on standard cross domain visual benchmarks.