I Am Guessing You Can't Recognize This: Generating Adversarial Images for Object Detection Using Spatial Commonsense (Student Abstract)
2020 ◽
Vol 34
(10)
◽
pp. 13789-13790
◽
Keyword(s):
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 øurmodel , 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.
2021 ◽
2019 ◽
Vol 33
◽
pp. 865-872
◽
2019 ◽
Vol 33
◽
pp. 5581-5588
◽
2020 ◽
Vol 34
(05)
◽
pp. 7618-7625
2016 ◽
Vol 55
◽
pp. 131-163
◽