# RDumb: A simple approach that questions our progress in continual test-time adaptation

arXiv: https://arxiv.org/abs/2306.05401 · HTML: https://mlsanity.com/paper/2306.05401/

## Key facts

- Cited by 53 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 56 references that are in the map.
- First posted on arXiv 8 Jun 2023.

## Builds on (most cited first, 30 of 43)

- [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)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [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)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization](https://mlsanity.com/paper/2006.16241/) (2020)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1702.05464/) (2017)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning](https://mlsanity.com/paper/1805.04687/) (2018)
- [Swin Transformer V2: Scaling Up Capacity and Resolution](https://mlsanity.com/paper/2111.09883/) (2021)
- [AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty](https://mlsanity.com/paper/1912.02781/) (2019)
- [Three scenarios for continual learning](https://mlsanity.com/paper/1904.07734/) (2019)
- [Exploring the Limits of Weakly Supervised Pretraining](https://mlsanity.com/paper/1805.00932/) (2018)
- [Continual Test-Time Domain Adaptation](https://mlsanity.com/paper/2203.13591/) (2022)
- [MaxViT: Multi-Axis Vision Transformer](https://mlsanity.com/paper/2204.01697/) (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)
- [CORe50: a New Dataset and Benchmark for Continuous Object Recognition](https://mlsanity.com/paper/1705.03550/) (2017)
- [Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shift](https://mlsanity.com/paper/2006.10963/) (2020)
- [Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer](https://mlsanity.com/paper/2012.07297/) (2020)
- [NOTE: Robust Continual Test-time Adaptation Against Temporal Correlation](https://mlsanity.com/paper/2208.05117/) (2022)
- [3D Common Corruptions and Data Augmentation](https://mlsanity.com/paper/2203.01441/) (2022)
- [Unsupervised Domain Adaptation through Self-Supervision](https://mlsanity.com/paper/1909.11825/) (2019)

## Built on by (most cited first, 30 of 53)

- [A Sober Look at Progress in Language Model Reasoning: Pitfalls and Paths to Reproducibility](https://mlsanity.com/paper/2504.07086/) (2025)
- [Investigating Continual Pretraining in Large Language Models: Insights and Implications](https://mlsanity.com/paper/2402.17400/) (2024)
- [DPCore: Dynamic Prompt Coreset for Continual Test-Time Adaptation](https://mlsanity.com/paper/2406.10737/) (2024)
- [The Entropy Enigma: Success and Failure of Entropy Minimization](https://mlsanity.com/paper/2405.05012/) (2024)
- [Uncertainty-Calibrated Test-Time Model Adaptation without Forgetting](https://mlsanity.com/paper/2403.11491/) (2024)
- [Unified Entropy Optimization for Open-Set Test-Time Adaptation](https://mlsanity.com/paper/2404.06065/) (2024)
- [Persistent Test-time Adaptation in Recurring Testing Scenarios](https://mlsanity.com/paper/2311.18193/) (2023)
- [STAMP: Outlier-Aware Test-Time Adaptation with Stable Memory Replay](https://mlsanity.com/paper/2407.15773/) (2024)
- [Discounted Adaptive Online Learning: Towards Better Regularization](https://mlsanity.com/paper/2402.02720/) (2024)
- [SCAP: Transductive Test-Time Adaptation via Supportive Clique-based Attribute Prompting](https://mlsanity.com/paper/2503.12866/) (2025)
- [Beyond Entropy: Region Confidence Proxy for Wild Test-Time Adaptation](https://mlsanity.com/paper/2505.20704/) (2025)
- [Monitoring Risks in Test-Time Adaptation](https://mlsanity.com/paper/2507.08721/) (2025)
- [Test-time Adaptation for Cross-modal Retrieval with Query Shift](https://mlsanity.com/paper/2410.15624/) (2024)
- [AETTA: Label-Free Accuracy Estimation for Test-Time Adaptation](https://mlsanity.com/paper/2404.01351/) (2024)
- [Reshaping the Online Data Buffering and Organizing Mechanism for Continual Test-Time Adaptation](https://mlsanity.com/paper/2407.09367/) (2024)
- [ReservoirTTA: Prolonged Test-time Adaptation for Evolving and Recurring Domains](https://mlsanity.com/paper/2505.14511/) (2025)
- [Temporal Test-Time Adaptation with State-Space Models](https://mlsanity.com/paper/2407.12492/) (2024)
- [Adapting Prediction Sets to Distribution Shifts Without Labels](https://mlsanity.com/paper/2406.01416/) (2024)
- [Fusion or Confusion? Multimodal Complexity Is Not All You Need](https://mlsanity.com/paper/2512.22991/) (2025)
- [When and Where to Reset Matters for Long-Term Test-Time Adaptation](https://mlsanity.com/paper/2603.03796/) (2026)
- [Efficient Open Set Single Image Test Time Adaptation of Vision Language Models](https://mlsanity.com/paper/2406.00481/) (2024)
- [Test-Time Adaptation with Binary Feedback](https://mlsanity.com/paper/2505.18514/) (2025)
- [Adapt in the Wild: Test-Time Entropy Minimization with Sharpness and Feature Regularization](https://mlsanity.com/paper/2509.04977/) (2025)
- [Class-aware Domain Knowledge Fusion and Fission for Continual Test-Time Adaptation](https://mlsanity.com/paper/2510.12150/) (2025)
- [Assessing Visually-Continuous Corruption Robustness of Neural Networks Relative to Human Performance](https://mlsanity.com/paper/2402.19401/) (2024)
- [Exploring Human-in-the-Loop Test-Time Adaptation by Synergizing Active Learning and Model Selection](https://mlsanity.com/paper/2405.18911/) (2024)
- [Improving self-training under distribution shifts via anchored confidence with theoretical guarantees](https://mlsanity.com/paper/2411.00586/) (2024)
- [CNS-Bench: Benchmarking Image Classifier Robustness Under Continuous Nuisance Shifts](https://mlsanity.com/paper/2507.17651/) (2025)
- [Dance Across Shifts: Forward-Facilitation Continual Test-Time Adaptation through Dynamic Style Bridging](https://mlsanity.com/paper/2605.18608/) (2026)
- [Maintain Plasticity in Long-timescale Continual Test-time Adaptation](https://mlsanity.com/paper/2412.20034/) (2024)

## Abstract (arXiv)

Test-Time Adaptation (TTA) allows to update pre-trained models to changing data distributions at deployment time. While early work tested these algorithms for individual fixed distribution shifts, recent work proposed and applied methods for continual adaptation over long timescales. To examine the reported progress in the field, we propose the Continually Changing Corruptions (CCC) benchmark to measure asymptotic performance of TTA techniques. We find that eventually all but one state-of-the-art methods collapse and perform worse than a non-adapting model, including models specifically proposed to be robust to performance collapse. In addition, we introduce a simple baseline, "RDumb", that periodically resets the model to its pretrained state. RDumb performs better or on par with the previously proposed state-of-the-art in all considered benchmarks. Our results show that previous TTA approaches are neither effective at regularizing adaptation to avoid collapse nor able to outperform a simplistic resetting strategy.