DEff-GAN: Diverse Attribute Transfer for Few-Shot Image Synthesis

Requirements of large amounts of data is a difficulty in training many GANs. Data efficient GANs involve fitting a generators continuous target distribution with a limited discrete set of data samples, which is a difficult task. Single image methods have focused on modeling the internal distribution of a single image and generating its samples. While single image methods can synthesize image samples with diversity, they do not model multiple images or capture the inherent relationship possible between two images. Given only a handful of images, we are interested in generating samples and exploiting the commonalities in the input images. In this work, we extend the single-image GAN method to model multiple images for sample synthesis. We modify the discriminator with an auxiliary classifier branch, which helps to generate a wide variety of samples and to classify the input labels. Our Data-Efficient GAN (DEff-GAN) generates excellent results when similarities and correspondences can be drawn between the input images or classes.

[1]  Xin Jin,et al.  Attribute Group Editing for Reliable Few-shot Image Generation , 2022, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Rajiv Kumar,et al.  The MIS Check-Dam Dataset for Object Detection and Instance Segmentation Tasks , 2021, VISIGRAPP.

[3]  Yang Gao,et al.  LoFGAN: Fusing Local Representations for Few-shot Image Generation , 2021, 2021 IEEE/CVF International Conference on Computer Vision (ICCV).

[4]  Hongdong Zhao,et al.  SA-SinGAN: self-attention for single-image generation adversarial networks , 2021, Machine Vision and Applications.

[5]  Juergen Gall,et al.  One-Shot GAN: Learning to Generate Samples from Single Images and Videos , 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[6]  Yong Jae Lee,et al.  Few-shot Image Generation via Cross-domain Correspondence , 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Supasorn Suwajanakorn,et al.  Repurposing GANs for One-Shot Semantic Part Segmentation , 2021, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  G. Sivakumar,et al.  Learning Unsupervised Cross-domain Image-to-Image Translation Using a Shared Discriminator , 2021, VISIGRAPP.

[9]  Yizhe Zhu,et al.  Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesis , 2021, ICLR.

[10]  Anurag Ranjan,et al.  MorphGAN: One-Shot Face Synthesis GAN for Detecting Recognition Bias , 2020, BMVC.

[11]  Liqing Zhang,et al.  DeltaGAN: Towards Diverse Few-shot Image Generation with Sample-Specific Delta , 2020, ECCV.

[12]  Yan Hong,et al.  F2GAN: Fusing-and-Filling GAN for Few-shot Image Generation , 2020, ACM Multimedia.

[13]  Song Han,et al.  Differentiable Augmentation for Data-Efficient GAN Training , 2020, NeurIPS.

[14]  Matthew Fisher,et al.  Improved Techniques for Training Single-Image GANs , 2020, 2021 IEEE Winter Conference on Applications of Computer Vision (WACV).

[15]  Yan Hong,et al.  Matchinggan: Matching-Based Few-Shot Image Generation , 2020, 2020 IEEE International Conference on Multimedia and Expo (ICME).

[16]  Zixuan Liu,et al.  DAWSON: A Domain Adaptive Few Shot Generation Framework , 2020, ArXiv.

[17]  Tero Karras,et al.  Analyzing and Improving the Image Quality of StyleGAN , 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[18]  Michal Irani,et al.  InGAN: Capturing and Retargeting the “DNA” of a Natural Image , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[19]  Jeff Donahue,et al.  Large Scale Adversarial Representation Learning , 2019, NeurIPS.

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

[21]  Louis Clouâtre,et al.  FIGR: Few-shot Image Generation with Reptile , 2019, ArXiv.

[22]  Wei Wang,et al.  Deep Learning for Single Image Super-Resolution: A Brief Review , 2018, IEEE Transactions on Multimedia.

[23]  Michal Irani,et al.  "Zero-Shot" Super-Resolution Using Deep Internal Learning , 2017, CVPR.

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

[25]  Thomas Brox,et al.  Generating Images with Perceptual Similarity Metrics based on Deep Networks , 2016, NIPS.

[26]  Xiaogang Wang,et al.  Deep Learning Face Attributes in the Wild , 2014, 2015 IEEE International Conference on Computer Vision (ICCV).

[27]  Nojun Kwak,et al.  Smoothing the Generative Latent Space with Mixup-based Distance Learning , 2021, ArXiv.

[28]  George Vogiatzis,et al.  rcGAN: Learning a Generative Model for Arbitrary Size Image Generation , 2020, ISVC.