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.

[1]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[2]  Alexei A. Efros,et al.  Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[3]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[4]  Baoyu Ma,et al.  A Method for Improving CNN-Based Image Recognition Using DCGAN , 2018 .

[5]  Yun Fu,et al.  Image Super-Resolution Using Very Deep Residual Channel Attention Networks , 2018, ECCV.

[6]  Soumith Chintala,et al.  Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks , 2015, ICLR.

[7]  Wojciech Zaremba,et al.  Improved Techniques for Training GANs , 2016, NIPS.

[8]  Mirella Lapata,et al.  Long Short-Term Memory-Networks for Machine Reading , 2016, EMNLP.

[9]  Pieter Abbeel,et al.  InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets , 2016, NIPS.

[10]  Simon Osindero,et al.  Conditional Generative Adversarial Nets , 2014, ArXiv.

[11]  Yoshua Bengio,et al.  Show, Attend and Tell: Neural Image Caption Generation with Visual Attention , 2015, ICML.

[12]  Jeff Donahue,et al.  Large Scale GAN Training for High Fidelity Natural Image Synthesis , 2018, ICLR.

[13]  Kilian Q. Weinberger,et al.  An empirical study on evaluation metrics of generative adversarial networks , 2018, ArXiv.

[14]  In-So Kweon,et al.  CBAM: Convolutional Block Attention Module , 2018, ECCV.

[15]  Sepp Hochreiter,et al.  GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium , 2017, NIPS.

[16]  Alexander J. Smola,et al.  Stacked Attention Networks for Image Question Answering , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  Aaron C. Courville,et al.  Improved Training of Wasserstein GANs , 2017, NIPS.

[18]  Jakob Uszkoreit,et al.  A Decomposable Attention Model for Natural Language Inference , 2016, EMNLP.

[19]  Alex Graves,et al.  DRAW: A Recurrent Neural Network For Image Generation , 2015, ICML.

[20]  Raymond Y. K. Lau,et al.  Least Squares Generative Adversarial Networks , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).

[21]  Christian Ledig,et al.  Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[22]  Chuanlong Li,et al.  Embedding Image Through Generated Intermediate Medium Using Deep Convolutional Generative Adversarial Network , 2018 .

[23]  Dimitris N. Metaxas,et al.  StackGAN: Text to Photo-Realistic Image Synthesis with Stacked Generative Adversarial Networks , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).