Black-box Explanation of Object Detectors via Saliency Maps
Authors
Authors
- Vitali Petsiuk
- Rajiv Jain
- Varun Manjunatha
- Vlad I. Morariu
- Ashutosh Mehra
- Vicente Ordonez
- Kate Saenko
Authors
- Vitali Petsiuk
- Rajiv Jain
- Varun Manjunatha
- Vlad I. Morariu
- Ashutosh Mehra
- Vicente Ordonez
- Kate Saenko
Published on
06/05/2020
We propose D-RISE, a method for generating visual explanations for the predictions of object detectors. D-RISE can be considered “black-box” in the software testing sense, it only needs access to the inputs and outputs of an object detector. Compared to gradient-based methods, D-RISE is more general and agnostic to the particular type of object detector being tested as it does not need to know about the inner workings of the model. We show that D-RISE can be easily applied to different object detectors including one-stage detectors such as YOLOv3 and two-stage detectors such as Faster-RCNN. We present a detailed analysis of the generated visual explanations to highlight the utilization of context and the possible biases learned by object detectors.
Please cite our work using the BibTeX below.
@misc{petsiuk2020blackbox,
title={Black-box Explanation of Object Detectors via Saliency Maps},
author={Vitali Petsiuk and Rajiv Jain and Varun Manjunatha and Vlad I. Morariu and Ashutosh Mehra and Vicente Ordonez and Kate Saenko},
year={2020},
eprint={2006.03204},
archivePrefix={arXiv},
primaryClass={cs.CV}
}