# Gradual Domain Adaptation without Indexed Intermediate Domains

arXiv: https://arxiv.org/abs/2207.04587 · HTML: https://mlsanity.com/paper/2207.04587/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Builds on 46 of its 101 references that are in the map.
- First posted on arXiv 11 Jul 2022.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks](https://mlsanity.com/paper/1706.02690/) (2017)
- [CyCADA: Cycle-Consistent Adversarial Domain Adaptation](https://mlsanity.com/paper/1711.03213/) (2017)
- [Improving Neural Machine Translation Models with Monolingual Data](https://mlsanity.com/paper/1511.06709/) (2015)
- [Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks](https://mlsanity.com/paper/1703.10593/) (2017)
- [Maximum Classifier Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1712.02560/) (2017)
- [Learning to Reweight Examples for Robust Deep Learning](https://mlsanity.com/paper/1803.09050/) (2018)
- [Deep Domain Confusion: Maximizing for Domain Invariance](https://mlsanity.com/paper/1412.3474/) (2014)
- [Confidence Regularized Self-Training](https://mlsanity.com/paper/1908.09822/) (2019)
- [Return of Frustratingly Easy Domain Adaptation](https://mlsanity.com/paper/1511.05547/) (2015)
- [Bidirectional Learning for Domain Adaptation of Semantic Segmentation](https://mlsanity.com/paper/1904.10620/) (2019)
- [Adversarial Domain Adaptation with Domain Mixup](https://mlsanity.com/paper/1912.01805/) (2019)
- [Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptation](https://mlsanity.com/paper/1803.11365/) (2018)
- [A DIRT-T Approach to Unsupervised Domain Adaptation](https://mlsanity.com/paper/1802.08735/) (2018)
- [Multi-Adversarial Domain Adaptation](https://mlsanity.com/paper/1809.02176/) (2018)
- [Theoretical Analysis of Self-Training with Deep Networks on Unlabeled Data](https://mlsanity.com/paper/2010.03622/) (2020)
- [DLOW: Domain Flow for Adaptation and Generalization](https://mlsanity.com/paper/1812.05418/) (2018)
- [Train in Germany, Test in The USA: Making 3D Object Detectors Generalize](https://mlsanity.com/paper/2005.08139/) (2020)
- [Understanding Self-Training for Gradual Domain Adaptation](https://mlsanity.com/paper/2002.11361/) (2020)
- [Dual Learning for Machine Translation](https://mlsanity.com/paper/1611.00179/) (2016)
- [Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspective](https://mlsanity.com/paper/2003.10780/) (2020)
- [Progressive Domain Adaptation for Object Detection](https://mlsanity.com/paper/1910.11319/) (2019)
- [Gradually Vanishing Bridge for Adversarial Domain Adaptation](https://mlsanity.com/paper/2003.13183/) (2020)
- [Domain Adaptation with Conditional Distribution Matching and Generalized Label Shift](https://mlsanity.com/paper/2003.04475/) (2020)

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

- [Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectives](https://mlsanity.com/paper/2307.16851/) (2023)
- [Curriculum Reinforcement Learning using Optimal Transport via Gradual Domain Adaptation](https://mlsanity.com/paper/2210.10195/) (2022)
- [Domain-Indexing Variational Bayes: Interpretable Domain Index for Domain Adaptation](https://mlsanity.com/paper/2302.02561/) (2023)
- [Gradual Domain Adaptation: Theory and Algorithms](https://mlsanity.com/paper/2310.13852/) (2023)
- [Pave Your Own Path: Graph Gradual Domain Adaptation on Fused Gromov-Wasserstein Geodesics](https://mlsanity.com/paper/2505.12709/) (2025)
- [Towards Open-World Segmentation of Parts](https://mlsanity.com/paper/2305.16804/) (2023)
- [Unified Out-Of-Distribution Detection: A Model-Specific Perspective](https://mlsanity.com/paper/2304.06813/) (2023)
- [Generalizing across Temporal Domains with Koopman Operators](https://mlsanity.com/paper/2402.07834/) (2024)
- [Introducing Intermediate Domains for Effective Self-Training during Test-Time](https://mlsanity.com/paper/2208.07736/) (2022)
- [Holistic Transfer: Towards Non-Disruptive Fine-Tuning with Partial Target Data](https://mlsanity.com/paper/2311.01420/) (2023)
- [Enhancing Evolving Domain Generalization through Dynamic Latent Representations](https://mlsanity.com/paper/2401.08464/) (2024)
- [Progressive Multi-Source Domain Adaptation for Personalized Facial Expression Recognition](https://mlsanity.com/paper/2504.04252/) (2025)
- [Evolving Domain Adaptation of Pretrained Language Models for Text Classification](https://mlsanity.com/paper/2311.09661/) (2023)
- [DA-CIL: Towards Domain Adaptive Class-Incremental 3D Object Detection](https://mlsanity.com/paper/2212.02057/) (2022)
- [Non-stationary Domain Generalization: Theory and Algorithm](https://mlsanity.com/paper/2405.06816/) (2024)
- [Zero Shot Domain Adaptive Semantic Segmentation by Synthetic Data Generation and Progressive Adaptation](https://mlsanity.com/paper/2508.03300/) (2025)
- [Gradual Domain Adaptation for Graph Learning](https://mlsanity.com/paper/2501.17443/) (2025)
- [Bidirectional Multi-Step Domain Generalization for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2403.10782/) (2024)
- [Incremental Uncertainty-aware Performance Monitoring with Active Labeling Intervention](https://mlsanity.com/paper/2505.07023/) (2025)
- [Self-Training with Dynamic Weighting for Robust Gradual Domain Adaptation](https://mlsanity.com/paper/2510.13864/) (2025)
- [Stratified Domain Adaptation: A Progressive Self-Training Approach for Scene Text Recognition](https://mlsanity.com/paper/2410.09913/) (2024)
- [Gradual Fine-Tuning with Graph Routing for Multi-Source Unsupervised Domain Adaptation](https://mlsanity.com/paper/2411.07185/) (2024)
- [SWAT: Sliding Window Adversarial Training for Gradual Domain Adaptation](https://mlsanity.com/paper/2501.19155/) (2025)
- [GDO:Gradual Domain Osmosis](https://mlsanity.com/paper/2501.19159/) (2025)
- [Rethinking the Flow-Based Gradual Domain Adaptation: A Semi-Dual Optimal Transport Perspective](https://mlsanity.com/paper/2602.01179/) (2026)
- [Optimal Training-Time Scaling in Gradual Adaptation](https://mlsanity.com/paper/2608.04927/) (2026)

## Abstract (arXiv)

The effectiveness of unsupervised domain adaptation degrades when there is a large discrepancy between the source and target domains. Gradual domain adaptation (GDA) is one promising way to mitigate such an issue, by leveraging additional unlabeled data that gradually shift from the source to the target. Through sequentially adapting the model along the "indexed" intermediate domains, GDA substantially improves the overall adaptation performance. In practice, however, the extra unlabeled data may not be separated into intermediate domains and indexed properly, limiting the applicability of GDA. In this paper, we investigate how to discover the sequence of intermediate domains when it is not already available. Concretely, we propose a coarse-to-fine framework, which starts with a coarse domain discovery step via progressive domain discriminator training. This coarse domain sequence then undergoes a fine indexing step via a novel cycle-consistency loss, which encourages the next intermediate domain to preserve sufficient discriminative knowledge of the current intermediate domain. The resulting domain sequence can then be used by a GDA algorithm. On benchmark data sets of GDA, we show that our approach, which we name Intermediate DOmain Labeler (IDOL), can lead to comparable or even better adaptation performance compared to the pre-defined domain sequence, making GDA more applicable and robust to the quality of domain sequences. Codes are available at https://github.com/hongyouc/IDOL.