CBAM-GAN: Generative Adversarial Networks Based on Convolutional Block Attention Module.

Generating images using generative adversarial networks (GAN) is one of the research hotspots. The traditional convolutional GAN treats spatial and channel-wise features equally, which causes the lack of flexibility in extracting features from the discriminator and the generator. To address the issue, we propose generative adversarial networks based on convolutional block attention module (CBAM-GAN) in this paper. CBAM-GAN adds the convolutional block attention module after some convolution operators to adaptively rescale spatial and channel-wise features, which can enhance salient regions and extract more detail features. We apply the network framework of CBAM-GAN to popular GAN models and do an empirical study on MNIST and CIFAR-10 datasets. Experiments show that our model can significantly improve the quality of generated images compared with the traditional convolutional GAN.