N-RPN: Hard Example Learning for Region Proposal Networks

TL;DR

This paper introduces nRPN, a negative region proposal network that learns from false positives to provide hard negatives, significantly improving the performance of region proposal networks in object detection tasks.

Contribution

The paper proposes nRPN, a novel method that enhances RPN training by learning from false positives to better handle hard negatives, leading to improved detection accuracy.

Findings

Reduced false positives in RPN

Improved performance on PASCAL VOC 2007

Effective hard negative mining strategy

Abstract

The region proposal task is to generate a set of candidate regions that contain an object. In this task, it is most important to propose as many candidates of ground-truth as possible in a fixed number of proposals. In a typical image, however, there are too few hard negative examples compared to the vast number of easy negatives, so region proposal networks struggle to train on hard negatives. Because of this problem, networks tend to propose hard negatives as candidates, while failing to propose ground-truth candidates, which leads to poor performance. In this paper, we propose a Negative Region Proposal Network(nRPN) to improve Region Proposal Network(RPN). The nRPN learns from the RPN's false positives and provide hard negative examples to the RPN. Our proposed nRPN leads to a reduction in false positives and better RPN performance. An RPN trained with an nRPN achieves performance improvements on the PASCAL VOC 2007 dataset.