# Stabilizing Open-Set Test-Time Adaptation via Primary-Auxiliary Filtering and Knowledge-Integrated Prediction

arXiv: https://arxiv.org/abs/2508.18751 · HTML: https://mlsanity.com/paper/2508.18751/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 31 references that are in the map.
- First posted on arXiv 26 Aug 2025.

## Builds on (most cited first, 23 of 23)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [Describing Textures in the Wild](https://mlsanity.com/paper/1311.3618/) (2013)
- [Sharpness-Aware Minimization for Efficiently Improving Generalization](https://mlsanity.com/paper/2010.01412/) (2020)
- [RobustBench: a standardized adversarial robustness benchmark](https://mlsanity.com/paper/2010.09670/) (2020)
- [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)
- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (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)
- [Robust Test-Time Adaptation in Dynamic Scenarios](https://mlsanity.com/paper/2303.13899/) (2023)
- [NOTE: Robust Continual Test-time Adaptation Against Temporal Correlation](https://mlsanity.com/paper/2208.05117/) (2022)
- [Robust Mean Teacher for Continual and Gradual Test-Time Adaptation](https://mlsanity.com/paper/2211.13081/) (2022)
- [Decorate the Newcomers: Visual Domain Prompt for Continual Test Time Adaptation](https://mlsanity.com/paper/2212.04145/) (2022)
- [DELTA: degradation-free fully test-time adaptation](https://mlsanity.com/paper/2301.13018/) (2023)
- [SoTTA: Robust Test-Time Adaptation on Noisy Data Streams](https://mlsanity.com/paper/2310.10074/) (2023)
- [ViDA: Homeostatic Visual Domain Adapter for Continual Test Time Adaptation](https://mlsanity.com/paper/2306.04344/) (2023)
- [A Probabilistic Framework for Lifelong Test-Time Adaptation](https://mlsanity.com/paper/2212.09713/) (2022)
- [Towards Open-Set Test-Time Adaptation Utilizing the Wisdom of Crowds in Entropy Minimization](https://mlsanity.com/paper/2308.06879/) (2023)
- [TeST: Test-time Self-Training under Distribution Shift](https://mlsanity.com/paper/2209.11459/) (2022)
- [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)
- [Un-Mixing Test-Time Normalization Statistics: Combatting Label Temporal Correlation](https://mlsanity.com/paper/2401.08328/) (2024)

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

- [COSTA: A Cluster-Centric Paradigm for Annotation-Free Open-Set Semantic Segmentation of Aerial Point Clouds with Domain Shifts](https://mlsanity.com/paper/2608.18479/) (2026)

## Abstract (arXiv)

Deep neural networks demonstrate strong performance under aligned training-test distributions. However, real-world test data often exhibit domain shifts. Test-Time Adaptation (TTA) addresses this challenge by adapting the model to test data during inference. While most TTA studies assume that the training and test data share the same class set (closed-set TTA), real-world scenarios often involve open-set data (open-set TTA), which can degrade closed-set accuracy. A recent study showed that identifying open-set data during adaptation and maximizing its entropy is an effective solution. However, the previous method relies on the source model for filtering, resulting in suboptimal filtering accuracy on domain-shifted test data. In contrast, we found that the adapting model, which learns domain knowledge from noisy test streams, tends to be unstable and leads to error accumulation when used for filtering. To address this problem, we propose Primary-Auxiliary Filtering (PAF), which employs an auxiliary filter to validate data filtered by the primary filter. Furthermore, we propose Knowledge-Integrated Prediction (KIP), which calibrates the outputs of the adapting model, EMA model, and source model to integrate their complementary knowledge for OSTTA. We validate our approach across diverse closed-set and open-set datasets. Our method enhances both closed-set accuracy and open-set discrimination over existing methods. The code is available at https://github.com/powerpowe/PAF-KIP-OSTTA .