A Unified Interactive Model Evaluation for Classification, Object Detection, and Instance Segmentation in Computer Vision
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.
Keywords
Cite
@article{arxiv.2308.05168,
title = {A Unified Interactive Model Evaluation for Classification, Object Detection, and Instance Segmentation in Computer Vision},
author = {Changjian Chen and Yukai Guo and Fengyuan Tian and Shilong Liu and Weikai Yang and Zhaowei Wang and Jing Wu and Hang Su and Hanspeter Pfister and Shixia Liu},
journal= {arXiv preprint arXiv:2308.05168},
year = {2023}
}
Comments
Accepted to IEEE VIS 2023