Adversarial Learning With Knowledge of Image Classification for Improving GANs

@article{Baek2019AdversarialLW,
  title={Adversarial Learning With Knowledge of Image Classification for Improving GANs},
  author={Jae-Yong Baek and Yong-Sang Yoo and Seung-Hwan Bae},
  journal={IEEE Access},
  year={2019},
  volume={7},
  pages={56591-56605}
}
Generating realistic images with fine details are still challenging due to difficulties of training GANs and mode collapse. To resolve this problem, our main idea is that leveraging the knowledge of an image classification network, which is pre-trained by a large scale dataset (e.g. ImageNet), would improve a GAN. By using the gradient of the network (i.e. discriminator) with high discriminability during training, we can, therefore, guide the gradient of a generator gradually toward the real… CONTINUE READING

References

Publications referenced by this paper.
SHOWING 1-10 OF 47 REFERENCES

Improved Techniques for Training GANs

VIEW 15 EXCERPTS
HIGHLY INFLUENTIAL

Generative Adversarial Nets

VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

Similar Papers

Loading similar papers…