# On the Robustness of Open-World Test-Time Training: Self-Training with Dynamic Prototype Expansion

arXiv: https://arxiv.org/abs/2308.09942 · HTML: https://mlsanity.com/paper/2308.09942/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 51 references that are in the map.
- First posted on arXiv 19 Aug 2023.

## Builds on (most cited first, 30 of 33)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [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)
- [Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2002.08546/) (2020)
- [Deep Visual Domain Adaptation: A Survey](https://mlsanity.com/paper/1802.03601/) (2018)
- [Continual Test-Time Domain Adaptation](https://mlsanity.com/paper/2203.13591/) (2022)
- [Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning](https://mlsanity.com/paper/1908.02983/) (2019)
- [Efficient Test-Time Model Adaptation without Forgetting](https://mlsanity.com/paper/2204.02610/) (2022)
- [VisDA: The Visual Domain Adaptation Challenge](https://mlsanity.com/paper/1710.06924/) (2017)
- [Towards Stable Test-Time Adaptation in Dynamic Wild World](https://mlsanity.com/paper/2302.12400/) (2023)
- [Recent Advances in Open Set Recognition: A Survey](https://mlsanity.com/paper/1811.08581/) (2018)
- [Contrastive Test-Time Adaptation](https://mlsanity.com/paper/2204.10377/) (2022)
- [Adversarial Domain Adaptation with Domain Mixup](https://mlsanity.com/paper/1912.01805/) (2019)
- [Do CIFAR-10 Classifiers Generalize to CIFAR-10?](https://mlsanity.com/paper/1806.00451/) (2018)
- [NOTE: Robust Continual Test-time Adaptation Against Temporal Correlation](https://mlsanity.com/paper/2208.05117/) (2022)
- [Open Set Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1804.10427/) (2018)
- [Cycle Self-Training for Domain Adaptation](https://mlsanity.com/paper/2103.03571/) (2021)
- [Source-free Domain Adaptation via Avatar Prototype Generation and Adaptation](https://mlsanity.com/paper/2106.15326/) (2021)
- [Infinite Mixture Prototypes for Few-Shot Learning](https://mlsanity.com/paper/1902.04552/) (2019)
- [Test-Time Adaptation via Conjugate Pseudo-labels](https://mlsanity.com/paper/2207.09640/) (2022)
- [Source-Free Domain Adaptation via Distribution Estimation](https://mlsanity.com/paper/2204.11257/) (2022)
- [Benchmarking Robustness of 3D Point Cloud Recognition Against Common Corruptions](https://mlsanity.com/paper/2201.12296/) (2022)
- [Discriminative Adversarial Domain Adaptation](https://mlsanity.com/paper/1911.12036/) (2019)
- [Reusing the Task-specific Classifier as a Discriminator: Discriminator-free Adversarial Domain Adaptation](https://mlsanity.com/paper/2204.03838/) (2022)
- [Evaluating the Adversarial Robustness of Adaptive Test-time Defenses](https://mlsanity.com/paper/2202.13711/) (2022)

## Built on by (most cited first, 30 of 34)

- [Prompt-based Adaptation in Large-scale Vision Models: A Survey](https://mlsanity.com/paper/2510.13219/) (2025)
- [T4P: Test-Time Training of Trajectory Prediction via Masked Autoencoder and Actor-specific Token Memory](https://mlsanity.com/paper/2403.10052/) (2024)
- [Unified Entropy Optimization for Open-Set Test-Time Adaptation](https://mlsanity.com/paper/2404.06065/) (2024)
- [STAMP: Outlier-Aware Test-Time Adaptation with Stable Memory Replay](https://mlsanity.com/paper/2407.15773/) (2024)
- [Towards Robust Multimodal Open-set Test-time Adaptation via Adaptive Entropy-aware Optimization](https://mlsanity.com/paper/2501.13924/) (2025)
- [Noisy Test-Time Adaptation in Vision-Language Models](https://mlsanity.com/paper/2502.14604/) (2025)
- [Generalized Incremental Learning under Concept Drift across Evolving Data Streams](https://mlsanity.com/paper/2506.05736/) (2025)
- [Synchronizing Task Behavior: Aligning Multiple Tasks during Test-Time Training](https://mlsanity.com/paper/2507.07778/) (2025)
- [Continual Adversarial Defense](https://mlsanity.com/paper/2312.09481/) (2023)
- [Memory-Efficient Pseudo-Labeling for Online Source-Free Universal Domain Adaptation using a Gaussian Mixture Model](https://mlsanity.com/paper/2407.14208/) (2024)
- [On the Adversarial Risk of Test Time Adaptation: An Investigation into Realistic Test-Time Data Poisoning](https://mlsanity.com/paper/2410.04682/) (2024)
- [Towards Understanding Extrapolation: a Causal Lens](https://mlsanity.com/paper/2501.09163/) (2025)
- [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)
- [Mixture-of-Experts for Open Set Domain Adaptation: A Dual-Space Detection Approach](https://mlsanity.com/paper/2311.00285/) (2023)
- [COMET: Contrastive Mean Teacher for Online Source-Free Universal Domain Adaptation](https://mlsanity.com/paper/2401.17728/) (2024)
- [Exploring Human-in-the-Loop Test-Time Adaptation by Synergizing Active Learning and Model Selection](https://mlsanity.com/paper/2405.18911/) (2024)
- [Covariance-based Space Regularization for Few-shot Class Incremental Learning](https://mlsanity.com/paper/2411.01172/) (2024)
- [TTL: Test-time Textual Learning for OOD Detection with Pretrained Vision-Language Models](https://mlsanity.com/paper/2604.15756/) (2026)
- [Dual Distribution Estimation for Zero-shot Noisy Test-Time Adaptation with VLMs](https://mlsanity.com/paper/2606.25758/) (2026)
- [Improving Batch Normalization with TTA for Robust Object Detection in Self-Driving](https://mlsanity.com/paper/2411.18860/) (2024)
- [From Pixel to Mask: A Survey of Out-of-Distribution Segmentation](https://mlsanity.com/paper/2508.10309/) (2025)
- [Instance-Aware Test-Time Segmentation for Continual Domain Shifts](https://mlsanity.com/paper/2512.08569/) (2025)
- [TALON: Test-time Adaptive Learning for On-the-Fly Category Discovery](https://mlsanity.com/paper/2603.08075/) (2026)
- [Mitigating the ID-OOD Tradeoff in Open-Set Test-Time Adaptation](https://mlsanity.com/paper/2604.01589/) (2026)
- [Open-World Test-Time Training: Self-Training with Contrast Learning](https://mlsanity.com/paper/2409.09591/) (2024)
- [Should Bias be Eliminated? A General Framework to Use Bias for OOD Generalization](https://mlsanity.com/paper/2507.17001/) (2025)
- [Hierarchical Adaptive networks with Task vectors for Test-Time Adaptation](https://mlsanity.com/paper/2508.09223/) (2025)
- [Segmentation Assisted Incremental Test Time Adaptation in an Open World](https://mlsanity.com/paper/2508.20029/) (2025)
- [PlugSI: Plug-and-Play Test-Time Graph Adaptation for Spatial Interpolation](https://mlsanity.com/paper/2602.09824/) (2026)

## Abstract (arXiv)

Generalizing deep learning models to unknown target domain distribution with low latency has motivated research into test-time training/adaptation (TTT/TTA). Existing approaches often focus on improving test-time training performance under well-curated target domain data. As figured out in this work, many state-of-the-art methods fail to maintain the performance when the target domain is contaminated with strong out-of-distribution (OOD) data, a.k.a. open-world test-time training (OWTTT). The failure is mainly due to the inability to distinguish strong OOD samples from regular weak OOD samples. To improve the robustness of OWTTT we first develop an adaptive strong OOD pruning which improves the efficacy of the self-training TTT method. We further propose a way to dynamically expand the prototypes to represent strong OOD samples for an improved weak/strong OOD data separation. Finally, we regularize self-training with distribution alignment and the combination yields the state-of-the-art performance on 5 OWTTT benchmarks. The code is available at https://github.com/Yushu-Li/OWTTT.