Document Type

Conference Proceeding

Publication Date

1-1-2020

Journal / Book Title

AAAI 2020 34th Aaai Conference on Artificial Intelligence

Abstract

Can we automatically predict failures of an object detection model on images from a target domain? We characterize errors of a state-of-the-art object detection model on the currently popular smart mobility domain, and find that a large number of errors can be identified using spatial commonsense. We propose CSK-SNIFFER, a system that automatically identifies a large number of such errors based on commonsense knowledge. Our system does not require any new annotations and can still find object detection errors with high accuracy (more than 80% when measured by humans). This work lays the foundation to answer exciting research questions on domain adaptation including the ability to automatically create adversarial datasets for target domain.

DOI

10.1609/aaai.v34i10.7166

Rights

Copyright © 2020, Association for the Advancement of Artificial Intelligence. This conference paper has been made Open Access under license by the publisher.

Published Citation

Garg, A., Tandon, N., & Varde, A. S. (2020). I Am Guessing You Can’t Recognize This: Generating Adversarial Images for Object Detection Using Spatial Commonsense (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 34(10), 13789-13790. https://doi.org/10.1609/aaai.v34i10.7166

Share

COinS