OoDAnalyzer: Interactive Analysis of Out-of-Distribution Samples

Abstract

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 paper, 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-based visualization. The detection method is improved from deep ensembles by combining more features with algorithms in the same family. To better analyze and understand the OoD samples in context, we have developed a novel kNN-based grid layout algorithm motivated by Hall's theorem. The algorithm approximates the optimal layout and has $O(k{N}^2)$ time complexity, faster than the grid layout algorithm with overall best performance but $O(N^3)$ time complexity. Quantitative evaluation and case studies were performed on several datasets to demonstrate the effectiveness and usefulness of OoDAnalyzer.

arXiv comment14 pages, 13 figures

References in corpus (6)

• Scikit-learn: Machine Learning in Python
• DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
• A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks
• A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks
• Multiplicative Normalizing Flows for Variational Bayesian Neural Networks
• Identifying Unknown Unknowns in the Open World: Representations and Policies for Guided Exploration