Generative Data Augmentation for Vehicle Detection in Aerial Images

TL;DR

This paper introduces a generative data augmentation technique for vehicle detection in aerial images, significantly improving detection accuracy without requiring additional supervision beyond bounding box annotations.

Contribution

The paper presents a generic generative augmentation method that enhances vehicle detection performance in aerial images, especially with limited training data, by increasing training instance diversity.

Findings

Increases Average Precision by up to 25.2% and 25.7%.

Effective with different generative models like Pluralistic and DeepFill.

Improves detection performance without extra supervision.

Abstract

Scarcity of training data is one of the prominent problems for deep networks which require large amounts data. Data augmentation is a widely used method to increase the number of training samples and their variations. In this paper, we focus on improving vehicle detection performance in aerial images and propose a generative augmentation method which does not need any extra supervision than the bounding box annotations of the vehicle objects in the training dataset. The proposed method increases the performance of vehicle detection by allowing detectors to be trained with higher number of instances, especially when there are limited number of training instances. The proposed method is generic in the sense that it can be integrated with different generators. The experiments show that the method increases the Average Precision by up to 25.2% and 25.7% when integrated with Pluralistic and DeepFill respectively.