Evaluating Machine Learning Models with NERO: Non-Equivariance Revealed on Orbits

TL;DR

NERO evaluation offers a novel, interactive approach to assess and visualize model equivariance and robustness across various tasks, moving beyond traditional scalar metrics to improve interpretability and model understanding.

Contribution

The paper introduces NERO, a new evaluation workflow with visualizations that reveal model equivariance and robustness, applicable across multiple research domains.

Findings

NERO effectively visualizes model equivariance properties.

NERO helps identify and interpret model weaknesses.

The approach is applicable to diverse tasks like recognition, detection, and 3D classification.

Abstract

Proper evaluations are crucial for better understanding, troubleshooting, interpreting model behaviors and further improving model performance. While using scalar-based error metrics provides a fast way to overview model performance, they are often too abstract to display certain weak spots and lack information regarding important model properties, such as robustness. This not only hinders machine learning models from being more interpretable and gaining trust, but also can be misleading to both model developers and users. Additionally, conventional evaluation procedures often leave researchers unclear about where and how model fails, which complicates model comparisons and further developments. To address these issues, we propose a novel evaluation workflow, named Non-Equivariance Revealed on Orbits (NERO) Evaluation. The goal of NERO evaluation is to turn focus from traditional scalar-based metrics onto evaluating and visualizing models equivariance, closely capturing model robustness, as well as to allow researchers quickly investigating interesting or unexpected model behaviors. NERO evaluation is consist of a task-agnostic interactive interface and a set of visualizations, called NERO plots, which reveals the equivariance property of the model. Case studies on how NERO evaluation can be applied to multiple research areas, including 2D digit recognition, object detection, particle image velocimetry (PIV), and 3D point cloud classification, demonstrate that NERO evaluation can quickly illustrate different model equivariance, and effectively explain model behaviors through interactive visualizations of the model outputs. In addition, we propose consensus, an alternative to ground truths, to be used in NERO evaluation so that model equivariance can still be evaluated with new, unlabeled datasets.