Bias Remediation in Driver Drowsiness Detection systems using Generative Adversarial Networks

no code implementations • 10 Dec 2019 • Mkhuseli Ngxande, Jules-Raymond Tapamo, Michael Burke

Our framework improves Convolutional Neural Network (CNN) trained for prediction by using Generative Adversarial networks (GAN) for targeted data augmentation based on a population bias visualisation strategy that groups faces with similar facial attributes and highlights where the model is failing.

Data Augmentation

DepthwiseGANs: Fast Training Generative Adversarial Networks for Realistic Image Synthesis

no code implementations • 6 Mar 2019 • Mkhuseli Ngxande, Jules-Raymond Tapamo, Michael Burke

In this paper, we investigate the use of depthwise separable convolutions to reduce training time while maintaining data generation performance.

Image Generation Super-Resolution +1