prajwalsingh / MSQ-GAN

Mode Seeking Quick GAN is a generative network which is combination of different GAN training strategies for fast and stable network training using sparse training data.

MSQ-GAN

Mode Seeking Quick GAN is a generative network which is combination of different GAN training strategies for fast and stable network training using sparse training data.

Results

Notes

• Work in progress.
• Not a clean code.

References

[1] Liu, Bingchen, et al. "Towards faster and stabilized gan training for high-fidelity few-shot image synthesis." International Conference on Learning Representations. 2020.

[2] Zhao, Shengyu, et al. "Differentiable augmentation for data-efficient gan training." Advances in Neural Information Processing Systems 33 (2020): 7559-7570.

[3] Karras, Tero, et al. "Progressive growing of gans for improved quality, stability, and variation." arXiv preprint arXiv:1710.10196 (2017).