MIX-MHingeGAN

Reported on 4 benchmarks across 2 tasks · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Medical2 results

Image GenerationonCIFAR-10
Inception score· 2020-07-13
10.21
best: 10.51 (StyleGAN2 + DiffAugment + D2D-CE)
SOTA
Lessons Learned from the Training of GANs on Artificial Datasets arXiv:2007.06418
Image GenerationonCIFAR-10
FID· 2020-07-13
3.6
best: 1.22 (GMem)
Lessons Learned from the Training of GANs on Artificial Datasets arXiv:2007.06418

Computer Vision2 results

Conditional Image GenerationonCIFAR-10
Inception score· 2020-07-13
10.21
best: 10.51 (StyleGAN2 + DiffAugment + D2D-CE)
SOTA
Lessons Learned from the Training of GANs on Artificial Datasets arXiv:2007.06418
Conditional Image GenerationonCIFAR-10
FID· 2020-07-13
3.6
best: 1.64 (EDM-G++ (conditional))
Lessons Learned from the Training of GANs on Artificial Datasets arXiv:2007.06418