Vendi Novelty Scores for Out-of-Distribution Detection
Vendi Novelty Scores for Out-of-Distribution Detection
Lewis-Sigler Institute For Integrative Genomics, Princeton University(普林斯顿大学整合基因组学研究所);Department of Computer Science, Princeton University(普林斯顿大学计算机科学系)
Out-of-distribution (OOD) detection is critical for the safe deployment of machine learning systems. Existing post-hoc detectors typically rely on model confidence scores or likelihood estimates in feature space, often under restrictive distributional assumptions. In this work, we introduce a third paradigm and formulate OOD detection from a diversity perspective. We propose the Vendi Novelty Score (VNS), an OOD detector based on the Vendi Scores (VS), a family of similarity-based diversity metrics. VNS quantifies how much a test sample increases the VS of the in-distribution feature set, providing a principled notion of novelty that does not require density modeling. VNS is linear-time, non-parametric, and naturally combines class-conditional (local) and dataset-level (global) novelty signals. Across multiple image classification benchmarks and network architectures, VNS achieves state-of-the-art OOD detection performance. Remarkably, VNS retains this performance when computed using only 1% of the training data, enabling deployment in memory- or access-constrained settings.
英文摘要:
Out-of-distribution (OOD) detection is critical for the safe deployment of machine learning systems. Existing post-hoc detectors typically rely on model confidence scores or likelihood estimates in feature space, often under restrictive distributional assumptions. In this work, we introduce a third paradigm and formulate OOD detection from a diversity perspective. We propose the Vendi Novelty Score (VNS), an OOD detector based on the Vendi Scores (VS), a family of similarity-based diversity metrics. VNS quantifies how much a test sample increases the VS of the in-distribution feature set, providing a principled notion of novelty that does not require density modeling. VNS is linear-time, non-parametric, and naturally combines class-conditional (local) and dataset-level (global) novelty signals. Across multiple image classification benchmarks and network architectures, VNS achieves state-of-the-art OOD detection performance. Remarkably, VNS retains this performance when computed using only 1% of the training data, enabling deployment in memory- or access-constrained settings.
How Much Is a Dataset Worth? Scaling Laws, the Vendi Score, and Matrix Spectral Functions
Department of Electrical & Computer Engineering(电气与计算机工程系);Paul G. Allen School of Computer Science & Engineering(保罗·G·艾伦计算机科学与工程学院);University of Washington(华盛顿大学)
Conditional Vendi Score: Prompt-Aware Diversity Evaluation for Generative AI Models and LLMs
Department of Computer Science and Engineering, The Chinese University of Hong Kong(计算机科学与工程系,香港中文大学);Department of Information Engineering, The Chinese University of Hong Kong(信息工程系,香港中文大学)
针对文本提示引导的生成模型,提出条件 Vendi 和条件 RKE 分数,通过条件熵分离模型自身多样性,并证明收敛性及在多个任务中恢复真实多样性排序。
The Alpha-Alternator: Dynamic Adaptation To Varying Noise Levels In Sequences Using The Vendi Score For Improved Robustness and Performance
Institute of Biomedical Engineering, University of Toronto(生物医学工程研究所,多伦多大学);Department of Computer Science, Princeton University(计算机科学系,普林斯顿大学);Vertaix
Beyond the Known: Adversarial Autoencoders in Novelty Detection
Machine Learning Research Group, School of Computer Science, University of Galway(戈尔韦大学计算机科学学院机器学习研究组);Insight SFI Research Centre for Data Analytics, University of Galway(戈尔韦大学Insight SFI数据分析研究中心);Valeo Vision Systems(法雷奥视觉系统公司)
SPARKE: Scalable Prompt-Aware Diversity and Novelty Guidance in Diffusion Models via RKE Score
Department of Computer Science and Engineering, The Chinese University of Hong Kong(计算机科学与工程系,香港中文大学);Department of Information Engineering, The Chinese University of Hong Kong(信息工程系,香港中文大学)