Missingness Bias in Model Debugging
Computer Vision and Pattern Recognition
2022-06-15 v2 Artificial Intelligence
Machine Learning
Abstract
Missingness, or the absence of features from an input, is a concept fundamental to many model debugging tools. However, in computer vision, pixels cannot simply be removed from an image. One thus tends to resort to heuristics such as blacking out pixels, which may in turn introduce bias into the debugging process. We study such biases and, in particular, show how transformer-based architectures can enable a more natural implementation of missingness, which side-steps these issues and improves the reliability of model debugging in practice. Our code is available at https://github.com/madrylab/missingness
Cite
@article{arxiv.2204.08945,
title = {Missingness Bias in Model Debugging},
author = {Saachi Jain and Hadi Salman and Eric Wong and Pengchuan Zhang and Vibhav Vineet and Sai Vemprala and Aleksander Madry},
journal= {arXiv preprint arXiv:2204.08945},
year = {2022}
}
Comments
Published at ICLR 2022