# Effective Restoration of Source Knowledge in Continual Test Time Adaptation

arXiv: https://arxiv.org/abs/2311.04991 · HTML: https://mlsanity.com/paper/2311.04991/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 36 references that are in the map.
- First posted on arXiv 8 Nov 2023.

## Builds on (most cited first, 28 of 28)

- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1702.05464/) (2017)
- [Deep Hashing Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1706.07522/) (2017)
- [Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2002.08546/) (2020)
- [RobustBench: a standardized adversarial robustness benchmark](https://mlsanity.com/paper/2010.09670/) (2020)
- [Learning to Adapt Structured Output Space for Semantic Segmentation](https://mlsanity.com/paper/1802.10349/) (2018)
- [Continual Test-Time Domain Adaptation](https://mlsanity.com/paper/2203.13591/) (2022)
- [Efficient Test-Time Model Adaptation without Forgetting](https://mlsanity.com/paper/2204.02610/) (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)
- [Revisiting Batch Normalization For Practical Domain Adaptation](https://mlsanity.com/paper/1603.04779/) (2016)
- [Source-Free Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2103.16372/) (2021)
- [Progressive Domain Adaptation for Object Detection](https://mlsanity.com/paper/1910.11319/) (2019)
- [The Norm Must Go On: Dynamic Unsupervised Domain Adaptation by Normalization](https://mlsanity.com/paper/2112.00463/) (2021)
- [EcoTTA: Memory-Efficient Continual Test-time Adaptation via Self-distilled Regularization](https://mlsanity.com/paper/2303.01904/) (2023)
- [TTN: A Domain-Shift Aware Batch Normalization in Test-Time Adaptation](https://mlsanity.com/paper/2302.05155/) (2023)
- [Unsupervised Multi-source Domain Adaptation Without Access to Source Data](https://mlsanity.com/paper/2104.01845/) (2021)
- [MM-TTA: Multi-Modal Test-Time Adaptation for 3D Semantic Segmentation](https://mlsanity.com/paper/2204.12667/) (2022)
- [Cross-domain Imitation from Observations](https://mlsanity.com/paper/2105.10037/) (2021)
- [On-the-Fly Test-time Adaptation for Medical Image Segmentation](https://mlsanity.com/paper/2203.05574/) (2022)
- [CoNMix for Source-free Single and Multi-target Domain Adaptation](https://mlsanity.com/paper/2211.03876/) (2022)
- [Cross-Modal Knowledge Transfer Without Task-Relevant Source Data](https://mlsanity.com/paper/2209.04027/) (2022)
- [Real-Time Anomaly Detection for Streaming Analytics](https://mlsanity.com/paper/1607.02480/) (2016)

## Built on by (most cited first, 15 of 15)

- [DPCore: Dynamic Prompt Coreset for Continual Test-Time Adaptation](https://mlsanity.com/paper/2406.10737/) (2024)
- [PCoTTA: Continual Test-Time Adaptation for Multi-Task Point Cloud Understanding](https://mlsanity.com/paper/2411.00632/) (2024)
- [Reshaping the Online Data Buffering and Organizing Mechanism for Continual Test-Time Adaptation](https://mlsanity.com/paper/2407.09367/) (2024)
- [MOS: Model Synergy for Test-Time Adaptation on LiDAR-Based 3D Object Detection](https://mlsanity.com/paper/2406.14878/) (2024)
- [Controllable Continual Test-Time Adaptation](https://mlsanity.com/paper/2405.14602/) (2024)
- [DPO: Dual-Perturbation Optimization for Test-time Adaptation in 3D Object Detection](https://mlsanity.com/paper/2406.13891/) (2024)
- [Continual Test-Time Adaptation for Object Detection with Adaptive Monitoring and Randomized Restoration](https://mlsanity.com/paper/2406.16439/) (2024)
- [Few Clicks Suffice: Active Test-Time Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2312.01835/) (2023)
- [Class-aware Domain Knowledge Fusion and Fission for Continual Test-Time Adaptation](https://mlsanity.com/paper/2510.12150/) (2025)
- [Dance Across Shifts: Forward-Facilitation Continual Test-Time Adaptation through Dynamic Style Bridging](https://mlsanity.com/paper/2605.18608/) (2026)
- [EmbodiTTA: Resource-Efficient Test-Time Adaptation for Embodied Visual Systems](https://mlsanity.com/paper/2505.00986/) (2025)
- [Continual Test-Time Adaptation in Computer Vision: Methods, Benchmarks, and Future Directions](https://mlsanity.com/paper/2607.08164/) (2026)
- [Domain Adaptation via Feature Refinement](https://mlsanity.com/paper/2508.16124/) (2025)
- [SloMo-Fast: Slow-Momentum and Fast-Adaptive Teachers for Source-Free Continual Test-Time Adaptation](https://mlsanity.com/paper/2511.18468/) (2025)
- [Source-Free Controlled Adaptation of Teachers for Continual Test-Time Adaptation](https://mlsanity.com/paper/2607.23735/) (2026)

## Abstract (arXiv)

Traditional test-time adaptation (TTA) methods face significant challenges in adapting to dynamic environments characterized by continuously changing long-term target distributions. These challenges primarily stem from two factors: catastrophic forgetting of previously learned valuable source knowledge and gradual error accumulation caused by miscalibrated pseudo labels. To address these issues, this paper introduces an unsupervised domain change detection method that is capable of identifying domain shifts in dynamic environments and subsequently resets the model parameters to the original source pre-trained values. By restoring the knowledge from the source, it effectively corrects the negative consequences arising from the gradual deterioration of model parameters caused by ongoing shifts in the domain. Our method involves progressive estimation of global batch-norm statistics specific to each domain, while keeping track of changes in the statistics triggered by domain shifts. Importantly, our method is agnostic to the specific adaptation technique employed and thus, can be incorporated to existing TTA methods to enhance their performance in dynamic environments. We perform extensive experiments on benchmark datasets to demonstrate the superior performance of our method compared to state-of-the-art adaptation methods.