Attention-Aware Generative Adversarial Networks (ATA-GANs)

In this work, we present a novel approach for training Generative Adversarial Networks (GANs). Using the attention maps produced by a Teacher Network we are able to improve the quality of the generated images as well as perform weakly supervised object localization on the generated images. To this end, we generate images of HEp-2 cells captured with Indirect Imunofluoresence (IIF) and study the ability of our network to perform a weakly localization of the cell. First, we demonstrate that whilst GANs can learn the mapping between the input domain and the target distribution efficiently, the discriminator network is not able to detect the regions of interest. Second, we present a novel attention transfer mechanism which allows us to enforce the discriminator to put emphasis on the regions of interest via transfer learning. Third, we show that this leads to more realistic images, as the discriminator learns to put emphasis on the area of interest. Fourth, the proposed method allows one to generate both images as well as attention maps which can be useful for data annotation e.g in object detection.