It GAN DO Better: GAN-based Detection of Objects on Images with Varying Quality

TL;DR

This paper introduces GAN-DO, a GAN-based framework that enhances object detection robustness on low-quality images without increasing model complexity, outperforming existing methods in accuracy.

Contribution

The novel GAN-DO framework improves object detection on degraded images by generating robust features, compatible with various architectures, without adding parameters or slowing inference.

Findings

GAN-DO increases detection accuracy on low-quality images.

GAN-DO outperforms existing methods in mean Average Precision (mAP).

The framework maintains baseline architecture complexity.

Abstract

In this paper, we propose in our novel generative framework the use of Generative Adversarial Networks (GANs) to generate features that provide robustness for object detection on reduced quality images. The proposed GAN-based Detection of Objects (GAN-DO) framework is not restricted to any particular architecture and can be generalized to several deep neural network (DNN) based architectures. The resulting deep neural network maintains the exact architecture as the selected baseline model without adding to the model parameter complexity or inference speed. We first evaluate the effect of image quality not only on the object classification but also on the object bounding box regression. We then test the models resulting from our proposed GAN-DO framework, using two state-of-the-art object detection architectures as the baseline models. We also evaluate the effect of the number of re-trained parameters in the generator of GAN-DO on the accuracy of the final trained model. Performance results provided using GAN-DO on object detection datasets establish an improved robustness to varying image quality and a higher mAP compared to the existing approaches.