A-Fast-RCNN: Hard Positive Generation via Adversary for Object Detection

July 2017

A-Fast-RCNN: Hard Positive Generation via Adversary for Object Detection

Conference Paper
Proceedings of (CVPR) Computer Vision and Pattern Recognition

Abstract:

How do we learn an object detector that is invariant to occlusions and deformations? Our current solution is to use a data-driven strategy -- collect large-scale datasets which have object instances under different conditions. The hope is that the final classifier can use these examples to learn invariances. But is it really possible to see all the occlusions in a dataset? We argue that like categories, occlusions and object deformations also follow a long-tail. Some occlusions and deformations are so rare that they hardly happen; yet we want to learn a model invariant to such occurrences. In this paper, we propose an alternative solution. We propose to learn an adversarial network that generates examples with occlusions and deformations. The goal of the adversary is to generate examples that are difficult for the object detector to classify. In our framework both the original detector and adversary are learned in a joint manner. Our experimental results indicate a 2.3% mAP boost on VOC07 and a 2.6% mAP boost on VOC2012 object detection challenge compared to the Fast-RCNN pipeline. We also release the code for this paper.
@conference{Wang-2017-113314,
author = {Xiaolong Wang And Abhinav Shrivastava And Abhinav Gupta},
title = {A-Fast-RCNN: Hard Positive Generation via Adversary for Object Detection},
booktitle = {Proceedings of (CVPR) Computer Vision and Pattern Recognition},
year = {2017},
month = {July},
pages = {3039 - 3048},
}
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.