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

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.

References in corpus (7)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• NIPS 2016 Tutorial: Generative Adversarial Networks
• Deep multi-scale video prediction beyond mean square error
• Examining the Impact of Blur on Recognition by Convolutional Networks
• How Image Degradations Affect Deep CNN-based Face Recognition?

Cited by in corpus (4)

• Galaxy Morphological Classification Catalogue of the Dark Energy Survey Year 3 data with Convolutional Neural Networks
• Prior Image-Constrained Reconstruction using Style-Based Generative Models
• TLGAN: document Text Localization using Generative Adversarial Nets
• A Generative Approach for Detection-driven Underwater Image Enhancement