2017年GAN 计算机视觉相关paper汇总

2017年GAN 计算机视觉相关paper汇总

主要收集从 2016年11月(CVPR2017 deadline)到现在的 生成对抗网络(GAN)相关paper (按arXiv发表顺序), 有遗漏欢迎补充。

  1. [1611.04076] Least Squares Generative Adversarial Networks (Cycle GAN的D用了其中的方法,将Loss改为L2 Loss,训练稳定性提高了,好于传统的cross-entropy loss)
  2. [1611.07004] Image-to-Image Translation with Conditional Adversarial Networks (pix2pix) 这篇中70x70的patchD在cyclegan中也有延续。 注:这篇中是pair来训练的
  3. [1612.05363] Learning Residual Images for Face Attribute Manipulation (CVPR 2017) 这一篇比较早就用dual learning了,比cycle gan都早了3个月啊。但是他用的cycle loss是D的Loss,而不是pixel level的L1 Loss。
  4. [1612.07828] Learning from Simulated and Unsupervised Images through Adversarial Training (CVPR 2017)
  5. [1701.07717] Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro (ICCV2017) 这篇索性拿G产生的图片来做数据增强,做了一个半监督学习框架,也容易理解。训传统分类ResNet,而没有使用D。 因为D现在还是比较浅?在Fine-grain dataset上也有提高。
  6. [1701.02676] Unsupervised Image-to-Image Translation with Generative Adversarial Networks 之前我们可以用cgan来指定生成什么domain。作者多加了一个分类器来预测随机input z(在学习映射完成后,z其实是有semantic含义的)所以如果除了c以外,我们还能指定z。
  7. [1701.07875] Wasserstein GAN
  8. [1703.02291] Triple Generative Adversarial Nets
  9. [1703.05192] DiscoGAN: Learning to Discover Cross-Domain Relations with Generative Adversarial Networks (ICML2017) 同一个世界,同一个梦想 喜欢这篇里面的图和实验。
  10. [1703.10593] CycleGAN: Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks (ICCV2017) 同一个世界,同一个梦想 代码很solid。 D用的是L2 Loss, Cycle Loss和Identity Loss都是L1 Loss。
  11. [1704.02510] DualGAN:Unsupervised Dual Learning for Image-to-Image Translation (ICCV2017) 同一个世界,同一个梦想
  12. [1704.00028] Improved Training of Wasserstein GANs
  13. Visual Saliency Prediction with Generative Adversarial Networks 阿岳感觉很一般
  14. Boosting Generative Models
  15. Towards Realistic High-Resolution Image Blending
  16. [1704.05838] Generative Face Completion
  17. [1704.04086] Global and Local Perception GAN for Photorealistic and Identity Preserving Frontal View Synthesis (ICCV 2017) 人脸pose旋转,需要pair来训练。一个网路做global的人脸,一个网络切5个关键点。最后融合到一起。
  18. [1704.04131] Neural Face Editing with Intrinsic Image Disentangling (CVPR2017)
  19. [1706.05274v2] Perceptual Generative Adversarial Networks for Small Object Detection
  20. Decomposing Motion and Content for Video Generation
  21. [1706.07068]Creative Adversarial Networks, Generating "Art" by Learning About Styles and Deviating from Style Norms 生成艺术作品
  22. [1707.03124] Adversarial Generation of Training Examples for Vehicle License Plate Recognition 用GAN来生成车牌,做数据增强


我的其他文章:

编辑于 2017-11-11

文章被以下专栏收录