DNA-GAN: Learning Disentangled Representations from Multi-Attribute Images

@article{Xiao2017DNAGANLD,
  title={DNA-GAN: Learning Disentangled Representations from Multi-Attribute Images},
  author={Taihong Xiao and Jiapeng Hong and Jinwen Ma},
  journal={CoRR},
  year={2017},
  volume={abs/1711.05415}
}
Disentangling factors of variation has become a very challenging problem on representation learning. Existing algorithms suffer from many limitations, such as unpredictable disentangling factors, poor quality of generated images from encodings, lack of identity information, etc. In this paper, we propose a supervised learning model called DNA-GAN which tries to disentangle different factors or attributes of images. The latent representations of images are DNA-like, in which each individual… CONTINUE READING
Recent Discussions
This paper has been referenced on Twitter 23 times over the past 90 days. VIEW TWEETS
6 Citations
24 References
Similar Papers

References

Publications referenced by this paper.
Showing 1-10 of 24 references

Similar Papers

Loading similar papers…