A unified interactive model evaluation for classification, object detection, and instance segmentation in computer vision

Chen, Changjian, Guo, Yukai, Tian, Fengyuan, Liu, Shilong, Yang, Weikai, Wang, Zhaowei, Wu, Jing ORCID: https://orcid.org/0000-0001-5123-9861, Su, Hang, Pfister, Hanspeter and Liu, Shixia 2023. A unified interactive model evaluation for classification, object detection, and instance segmentation in computer vision. Presented at: IEEE VIS 2023, Melbourne, Australia, 22-27 October 2023. IEEE Transactions on Visualization and Computer Graphics. Institute of Electrical and Electronics Engineers, 10.1109/TVCG.2023.3326588

Preview

PDF - Accepted Post-Print Version Download (8MB) | Preview

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

Item Type:	Conference or Workshop Item (Paper)
Date Type:	Published Online
Status:	In Press
Schools:	Computer Science & Informatics
Publisher:	Institute of Electrical and Electronics Engineers
ISSN:	1077-2626
Date of First Compliant Deposit:	2 October 2023
Date of Acceptance:	16 July 2023
Last Modified:	07 Dec 2023 13:52
URI:	https://orca.cardiff.ac.uk/id/eprint/162859

Actions (repository staff only)

Edit Item