# Introducing Intermediate Domains for Effective Self-Training during Test-Time

arXiv: https://arxiv.org/abs/2208.07736 · HTML: https://mlsanity.com/paper/2208.07736/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 47 of its 63 references that are in the map.
- First posted on arXiv 16 Aug 2022.

## Builds on (most cited first, 30 of 47)

- [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)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [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)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization](https://mlsanity.com/paper/2006.16241/) (2020)
- [Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World](https://mlsanity.com/paper/1703.06907/) (2017)
- [BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning](https://mlsanity.com/paper/1805.04687/) (2018)
- [CyCADA: Cycle-Consistent Adversarial Domain Adaptation](https://mlsanity.com/paper/1711.03213/) (2017)
- [AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty](https://mlsanity.com/paper/1912.02781/) (2019)
- [Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2002.08546/) (2020)
- [Playing for Data: Ground Truth from Computer Games](https://mlsanity.com/paper/1608.02192/) (2016)
- [RobustBench: a standardized adversarial robustness benchmark](https://mlsanity.com/paper/2010.09670/) (2020)
- [Domain Generalization via Invariant Feature Representation](https://mlsanity.com/paper/1301.2115/) (2013)
- [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)
- [Continual Test-Time Domain Adaptation](https://mlsanity.com/paper/2203.13591/) (2022)
- [Improving robustness against common corruptions by covariate shift adaptation](https://mlsanity.com/paper/2006.16971/) (2020)
- [MEMO: Test Time Robustness via Adaptation and Augmentation](https://mlsanity.com/paper/2110.09506/) (2021)
- [Bidirectional Learning for Domain Adaptation of Semantic Segmentation](https://mlsanity.com/paper/1904.10620/) (2019)
- [DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation](https://mlsanity.com/paper/2111.14887/) (2021)
- [Training Deep Networks with Synthetic Data: Bridging the Reality Gap by Domain Randomization](https://mlsanity.com/paper/1804.06516/) (2018)
- [Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2101.10979/) (2021)
- [Contrastive Test-Time Adaptation](https://mlsanity.com/paper/2204.10377/) (2022)

## Built on by (most cited first, 12 of 12)

- [Robust Mean Teacher for Continual and Gradual Test-Time Adaptation](https://mlsanity.com/paper/2211.13081/) (2022)
- [Universal Test-time Adaptation through Weight Ensembling, Diversity Weighting, and Prior Correction](https://mlsanity.com/paper/2306.00650/) (2023)
- [Benchmarking Test-Time Adaptation against Distribution Shifts in Image Classification](https://mlsanity.com/paper/2307.03133/) (2023)
- [Learning to Adapt Frozen CLIP for Few-Shot Test-Time Domain Adaptation](https://mlsanity.com/paper/2506.17307/) (2025)
- [Distribution Alignment for Fully Test-Time Adaptation with Dynamic Online Data Streams](https://mlsanity.com/paper/2407.12128/) (2024)
- [Calibration-free online test-time adaptation for electroencephalography motor imagery decoding](https://mlsanity.com/paper/2311.18520/) (2023)
- [A Lost Opportunity for Vision-Language Models: A Comparative Study of Online Test-Time Adaptation for Vision-Language Models](https://mlsanity.com/paper/2405.14977/) (2024)
- [Self-Training with Dynamic Weighting for Robust Gradual Domain Adaptation](https://mlsanity.com/paper/2510.13864/) (2025)
- [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)
- [SloMo-Fast: Slow-Momentum and Fast-Adaptive Teachers for Source-Free Continual Test-Time Adaptation](https://mlsanity.com/paper/2511.18468/) (2025)
- [Rethinking the Teacher-Student Framework for Test-Time Adaptation](https://mlsanity.com/paper/2609.02507/) (2026)

## Abstract (arXiv)

Experiencing domain shifts during test-time is nearly inevitable in practice and likely results in a severe performance degradation. To overcome this issue, test-time adaptation continues to update the initial source model during deployment. A promising direction are methods based on self-training which have been shown to be well suited for gradual domain adaptation, since reliable pseudo-labels can be provided. In this work, we address two problems that exist when applying self-training in the setting of test-time adaptation. First, adapting a model to long test sequences that contain multiple domains can lead to error accumulation. Second, naturally, not all shifts are gradual in practice. To tackle these challenges, we introduce GTTA. By creating artificial intermediate domains that divide the current domain shift into a more gradual one, effective self-training through high quality pseudo-labels can be performed. To create the intermediate domains, we propose two independent variations: mixup and light-weight style transfer. We demonstrate the effectiveness of our approach on the continual and gradual corruption benchmarks, as well as ImageNet-R. To further investigate gradual shifts in the context of urban scene segmentation, we publish a new benchmark: CarlaTTA. It enables the exploration of several non-stationary domain shifts.