An Improved Self-supervised GAN via Adversarial Training

@article{Tran2019AnIS,
  title={An Improved Self-supervised GAN via Adversarial Training},
  author={Ngoc-Trung Tran and Viet-Hung Tran and Ngoc-Bao Nguyen and Ngai-Man Cheung},
  journal={ArXiv},
  year={2019},
  volume={abs/1905.05469}
}
We propose to improve unconditional Generative Adversarial Networks (GAN) by training the self-supervised learning with the adversarial process. In particular, we apply self-supervised learning via the geometric transformation on input images and assign the pseudo-labels to these transformed images. (i) In addition to the GAN task, which distinguishes data (real) versus generated (fake) samples, we train the discriminator to predict the correct pseudo-labels of real transformed samples… CONTINUE READING
5
Twitter Mentions

References

Publications referenced by this paper.
SHOWING 1-10 OF 35 REFERENCES

Similar Papers

Loading similar papers…