OoDAnalyzer: Interactive Analysis of Out-of-Distribution Samples.
IEEE Transactions on Visualization and Computer Graphics(2021)
摘要
One major cause of performance degradation in predictive models is that the test samples are not well covered by the training data. Such not well-represented samples are called OoD samples. In this article, we propose OoDAnalyzer, a visual analysis approach for interactively identifying OoD samples and explaining them in context. Our approach integrates an ensemble OoD detection method and a grid-...
更多查看译文
关键词
Training,Layout,Visualization,Dogs,Feature extraction,Approximation algorithms,Cats
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要