A Unified Interactive Model Evaluation for Classification, Object Detection, and Instance Segmentation in Computer Vision

TL;DR

This paper introduces Uni-Evaluator, an open-source visual analysis tool that provides a unified evaluation framework for classification, object detection, and instance segmentation models in computer vision, enhancing interpretability and diagnostics.

Contribution

The paper presents a novel unified evaluation approach and visualization toolkit that supports multiple complex vision tasks within a single framework, filling a gap in existing tools.

Findings

Effective visualization of model performance across tasks

Identification of problematic data subsets

Facilitated model improvement decisions

Abstract

Existing model evaluation tools mainly focus on evaluating classification models, leaving a gap in evaluating more complex models, such as object detection. In this paper, we develop an open-source visual analysis tool, Uni-Evaluator, to support a unified model evaluation for classification, object detection, and instance segmentation in computer vision. The key idea behind our method is to formulate both discrete and continuous predictions in different tasks as unified probability distributions. Based on these distributions, we develop 1) a matrix-based visualization to provide an overview of model performance; 2) a table visualization to identify the problematic data subsets where the model performs poorly; 3) a grid visualization to display the samples of interest. These visualizations work together to facilitate the model evaluation from a global overview to individual samples. Two case studies demonstrate the effectiveness of Uni-Evaluator in evaluating model performance and making informed improvements.