# Less is More: Pseudo-Label Filtering for Continual Test-Time Adaptation

arXiv: https://arxiv.org/abs/2406.02609 · HTML: https://mlsanity.com/paper/2406.02609/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 48 references that are in the map.
- First posted on arXiv 3 Jun 2024.

## Builds on (most cited first, 24 of 24)

- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [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)
- [Domain Generalization via Invariant Feature Representation](https://mlsanity.com/paper/1301.2115/) (2013)
- [Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results](https://mlsanity.com/paper/1703.01780/) (2017)
- [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)
- [Revisiting Batch Normalization For Practical Domain Adaptation](https://mlsanity.com/paper/1603.04779/) (2016)
- [A Fourier Perspective on Model Robustness in Computer Vision](https://mlsanity.com/paper/1906.08988/) (2019)
- [FreeMatch: Self-adaptive Thresholding for Semi-supervised Learning](https://mlsanity.com/paper/2205.07246/) (2022)
- [Tent: Fully Test-time Adaptation by Entropy Minimization](https://mlsanity.com/paper/2006.10726/) (2020)
- [SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMs](https://mlsanity.com/paper/2404.13081/) (2024)
- [MT3: Meta Test-Time Training for Self-Supervised Test-Time Adaption](https://mlsanity.com/paper/2103.16201/) (2021)
- [Test-Time Training with Self-Supervision for Generalization under Distribution Shifts](https://mlsanity.com/paper/1909.13231/) (2019)
- [IEBins: Iterative Elastic Bins for Monocular Depth Estimation](https://mlsanity.com/paper/2309.14137/) (2023)
- [Exploring Example Influence in Continual Learning](https://mlsanity.com/paper/2209.12241/) (2022)
- [Sinkhorn Label Allocation: Semi-Supervised Classification via Annealed Self-Training](https://mlsanity.com/paper/2102.08622/) (2021)
- [Switching Temporary Teachers for Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2310.18640/) (2023)
- [Commonsense Prototype for Outdoor Unsupervised 3D Object Detection](https://mlsanity.com/paper/2404.16493/) (2024)
- [PG-LBO: Enhancing High-Dimensional Bayesian Optimization with Pseudo-Label and Gaussian Process Guidance](https://mlsanity.com/paper/2312.16983/) (2023)
- [TTAPS: Test-Time Adaption by Aligning Prototypes using Self-Supervision](https://mlsanity.com/paper/2205.08731/) (2022)
- [PALM: Pushing Adaptive Learning Rate Mechanisms for Continual Test-Time Adaptation](https://mlsanity.com/paper/2403.10650/) (2024)
- [DomainVerse: A Benchmark Towards Real-World Distribution Shifts For Tuning-Free Adaptive Domain Generalization](https://mlsanity.com/paper/2403.02714/) (2024)
- [Geometric Data Augmentations to Mitigate Distribution Shifts in Pollen Classification from Microscopic Images](https://mlsanity.com/paper/2311.11029/) (2023)

## Built on by (most cited first, 1 of 1)

- [The Golden Subspace: Where Efficiency Meets Generalization in Continual Test-Time Adaptation](https://mlsanity.com/paper/2603.21928/) (2026)

## Abstract (arXiv)

Continual Test-Time Adaptation (CTTA) aims to adapt a pre-trained model to a sequence of target domains during the test phase without accessing the source data. To adapt to unlabeled data from unknown domains, existing methods rely on constructing pseudo-labels for all samples and updating the model through self-training. However, these pseudo-labels often involve noise, leading to insufficient adaptation. To improve the quality of pseudo-labels, we propose a pseudo-label selection method for CTTA, called Pseudo Labeling Filter (PLF). The key idea of PLF is to keep selecting appropriate thresholds for pseudo-labels and identify reliable ones for self-training. Specifically, we present three principles for setting thresholds during continuous domain learning, including initialization, growth and diversity. Based on these principles, we design Self-Adaptive Thresholding to filter pseudo-labels. Additionally, we introduce a Class Prior Alignment (CPA) method to encourage the model to make diverse predictions for unknown domain samples. Through extensive experiments, PLF outperforms current state-of-the-art methods, proving its effectiveness in CTTA.