{"slug": "reliable-neural-collapse-approximation-for-open-world-test-time-adaptation", "title": "Reliable Neural Collapse Approximation for Open-World Test-Time Adaptation", "summary": "Researchers at an undisclosed institution introduced Reliable Neural Collapse approximation (ReNC), a method for Open-World Test-Time Adaptation (OWTTA) that uses neural collapse as a structural prior to filter out-of-distribution samples and refine prototypes for reliable target-domain adaptation. In experiments on several open-world benchmarks, ReNC outperformed existing TTA methods and better preserved neural collapse properties, with code available at https://github.com/JiaqiLin-AI/ReNC.", "body_md": "arXiv:2608.19890v1 Announce Type: new\nAbstract: Test-Time Adaptation (TTA) methods aim to bridge the domain gap between the source and target domains. However, traditional TTA methods become ineffective when the label distribution shift occurs, a challenge commonly referred to as an open-world scenario. In this paper, we introduce a new method named Reliable Neural Collapse approximation (ReNC) for Open-World Test-Time Adaptation (OWTTA). Specifically, we leverage neural collapse as a structural prior for reliable target-domain adaptation. Guided by this prior, we justify that the pre-trained classifier weights can serve as the prototypes of the source domain. By measuring the similarity between samples and prototypes, we filter out the Out-Of-Distribution~(OOD) samples for reliable updates. Furthermore, we propose a neural collapse approximation mechanism to refine these prototypes, ensuring they can gradually adapt to the target domain while maintaining the neural collapse structure. Extensive experiments on several open-world benchmarks demonstrate the superiority of the proposed method. Our empirical analysis suggests that ReNC better preserves NC-related properties in the target domain, providing useful evidence for explaining reliable OWTTA and offering new insights for model design. Code is available at https://github.com/JiaqiLin-AI/ReNC.", "url": "https://wpnews.pro/news/reliable-neural-collapse-approximation-for-open-world-test-time-adaptation", "canonical_source": "https://www.machinebrief.com/news/reliable-neural-collapse-approximation-for-open-world-test-t-cnxo", "published_at": "2026-08-21 04:00:00+00:00", "updated_at": "2026-08-21 04:14:38.382580+00:00", "lang": "en", "topics": ["machine-learning", "artificial-intelligence"], "entities": ["ReNC", "Open-World Test-Time Adaptation", "arXiv"], "alternates": {"html": "https://wpnews.pro/news/reliable-neural-collapse-approximation-for-open-world-test-time-adaptation", "markdown": "https://wpnews.pro/news/reliable-neural-collapse-approximation-for-open-world-test-time-adaptation.md", "text": "https://wpnews.pro/news/reliable-neural-collapse-approximation-for-open-world-test-time-adaptation.txt", "jsonld": "https://wpnews.pro/news/reliable-neural-collapse-approximation-for-open-world-test-time-adaptation.jsonld"}}