Problem
Research questions and friction points this paper is trying to address.
Test-Time Adaptation
Open-World Scenario
Label Distribution Shift
Reliable Neural Collapse Approximation for Open-World Test-Time Adaptation
🤖 AI Summary
本文提出了一种名为ReNC的新方法，通过利用神经崩溃作为结构先验来解决开放世界测试时适应中的标签分布偏移问题。
📝 Abstract
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.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Reliable Neural Collapse
Open-World Test-Time Adaptation
Out-Of-Distribution samples
🔎 Similar Papers
No similar papers found.
