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(kN 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.

ESCAPE: Countering Systematic Errors from Machine’s Blind Spots via Interactive Visual Analysis

“…Visual analytic tools can also help inspect and explain the potential cause of systematic failures such as a shifted or skewed distribution of the training examples termed as out-of-distribution [12], covariate or concept shift [58] or machine biases [1,10,57]. The OoD analyzer [12] presented a grid-based layout to visualize the distributional differences in training and test sets. The problem of concept drift was tackled and presented as visualizations in a 2D heatmap visualization [58] or distribution-based scatterplot [56].…”