Sequential Cross Attention Based Multi-Task Learning

in many applied computer vision tasks, training data is a scarce resource. This can result in poor performance of deep neural networks trained via supervised learning. We propose an approach to help boost performance in small training data regimes. Our method, called "CONGA", uses a CONditional Gan to Augment training data. Unlike previous work it can be added to any target discriminative model and allows the trade-off of computational cost for improved training sample efficiency. To further improve the quality of generated images and our method's performance, and distinct from normal conditional GANs, we also propose to supervise the generator's output via the target model. We compare our approach to similarly motivated methods on various image classification datasets (CIFAR-10, CIFAR-100, and Street View House Numbers), showing significant quantitative improvements.