Enhanced balancing GAN: minority-class image generation

Generative adversarial networks (GANs) are one of the most powerful generative models, but always require a large and balanced dataset to train. Traditional GANs are not applicable to generate minority-class images in a highly imbalanced dataset. Balancing GAN (BAGAN) is proposed to mitigate this problem, but it is unstable when images in different classes look similar, e.g. flowers and cells. In this work, we propose a supervised autoencoder with an intermediate embedding model to disperse the labeled latent vectors. With the improved autoencoder initialization, we also build an architecture of BAGAN with gradient penalty (BAGAN-GP). Our proposed model overcomes the unstable issue in original BAGAN and converges faster to high quality generations. Our model achieves high performance on the imbalanced scale-down version of MNIST Fashion, CIFAR-10, and one small-scale medical image dataset.

[1]  Abdullah M. Iliyasu,et al.  Deploying Machine and Deep Learning Models for Efficient Data-Augmented Detection of COVID-19 Infections , 2020, Viruses.

[2]  Michael I. Jordan,et al.  Advances in Neural Information Processing Systems 30 , 1995 .

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

[4]  Jaakko Lehtinen,et al.  Progressive Growing of GANs for Improved Quality, Stability, and Variation , 2017, ICLR.

[5]  Yann LeCun,et al.  Energy-based Generative Adversarial Networks , 2016, ICLR.

[6]  David Berthelot,et al.  BEGAN: Boundary Equilibrium Generative Adversarial Networks , 2017, ArXiv.

[7]  D. Dowson,et al.  The Fréchet distance between multivariate normal distributions , 1982 .

[8]  Harshad Rai,et al.  Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks , 2018 .

[9]  Jeffrey L. Gunter,et al.  Medical Image Synthesis for Data Augmentation and Anonymization using Generative Adversarial Networks , 2018, SASHIMI@MICCAI.

[10]  Han Zhang,et al.  Self-Attention Generative Adversarial Networks , 2018, ICML.

[11]  Andrew M. Dai,et al.  Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Step , 2017, ICLR.

[12]  Jacob D. Abernethy,et al.  How to Train Your DRAGAN , 2017, ArXiv.

[13]  Jonathon Shlens,et al.  Conditional Image Synthesis with Auxiliary Classifier GANs , 2016, ICML.

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

[15]  Léon Bottou,et al.  Wasserstein GAN , 2017, ArXiv.

[16]  Charles A. Sutton,et al.  VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning , 2017, NIPS.

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

[18]  Guo-Jun Qi,et al.  Loss-Sensitive Generative Adversarial Networks on Lipschitz Densities , 2017, International Journal of Computer Vision.

[19]  Shang-Hong Lai,et al.  AugGAN: Cross Domain Adaptation with GAN-Based Data Augmentation , 2018, ECCV.

[20]  Yann LeCun,et al.  Energy-based Generative Adversarial Network , 2016, ICLR.

[21]  Jacob Abernethy,et al.  On Convergence and Stability of GANs , 2018 .

[22]  Taghi M. Khoshgoftaar,et al.  A survey on Image Data Augmentation for Deep Learning , 2019, Journal of Big Data.

[23]  Nassir Navab,et al.  GANs for Medical Image Analysis , 2018, Artif. Intell. Medicine.

[24]  Constantine Bekas,et al.  BAGAN: Data Augmentation with Balancing GAN , 2018, ArXiv.

[25]  Yun Luo,et al.  EEG Data Augmentation for Emotion Recognition Using a Conditional Wasserstein GAN , 2018, 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[26]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[27]  Tali Dekel,et al.  SinGAN: Learning a Generative Model From a Single Natural Image , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[28]  Philip Bachman,et al.  Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Data , 2018, ICML.

[29]  Zhenan Sun,et al.  A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications , 2020, IEEE Transactions on Knowledge and Data Engineering.

[30]  Rishi Sharma,et al.  A Note on the Inception Score , 2018, ArXiv.

[31]  Shin'ichi Satoh,et al.  Learning More with Less: Conditional PGGAN-based Data Augmentation for Brain Metastases Detection Using Highly-Rough Annotation on MR Images , 2019, CIKM.

[32]  Sankha Subhra Mullick,et al.  Generative Adversarial Minority Oversampling , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).