DASH: Visual Analytics for Debiasing Image Classification via User-Driven Synthetic Data Augmentation
Loading...
Date
2022
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association
Abstract
Image classification models often learn to predict a class based on irrelevant co-occurrences between input features and an output class in training data. We call the unwanted correlations ''data biases,'' and the visual features causing data biases ''bias factors.'' It is challenging to identify and mitigate biases automatically without human intervention. Therefore, we conducted a design study to find a human-in-the-loop solution. First, we identified user tasks that capture the bias mitigation process for image classification models with three experts. Then, to support the tasks, we developed a visual analytics system called DASH that allows users to visually identify bias factors, to iteratively generate synthetic images using a state-of-the-art image-toimage translation model, and to supervise the model training process for improving the classification accuracy. Our quantitative evaluation and qualitative study with ten participants demonstrate the usefulness of DASH and provide lessons for future work.
Description
CCS Concepts: Human-centered computing --> Visual analytics
@inproceedings{10.2312:evs.20221099,
booktitle = {EuroVis 2022 - Short Papers},
editor = {Agus, Marco and Aigner, Wolfgang and Hoellt, Thomas},
title = {{DASH: Visual Analytics for Debiasing Image Classification via User-Driven Synthetic Data Augmentation}},
author = {Kwon, Bum Chul and Lee, Jungsoo and Chung, Chaeyeon and Lee, Nyoungwoo and Choi, Ho-Jin and Choo, Jaegul},
year = {2022},
publisher = {The Eurographics Association},
ISBN = {978-3-03868-184-7},
DOI = {10.2312/evs.20221099}
}