VQ-GAN

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

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

Audio2 results

10-shot image generationonConceptual Captions
FID· 2020-12-17
28.86
best: 9.8 (Contextual RQ-Transformer)
SOTA
Taming Transformers for High-Resolution Image Synthesis arXiv:2012.09841
1 Image, 2*2 StitchionConceptual Captions
FID· 2020-12-17
28.86
best: 9.8 (Contextual RQ-Transformer)
SOTA
Taming Transformers for High-Resolution Image Synthesis arXiv:2012.09841

Medical1 result

Image GenerationonConceptual Captions
FID· 2020-12-17
28.86
best: 9.8 (Contextual RQ-Transformer)
SOTA
Taming Transformers for High-Resolution Image Synthesis arXiv:2012.09841

Natural Language Processing1 result

Text-to-Image GenerationonConceptual Captions
FID· 2020-12-17
28.86
best: 9.8 (Contextual RQ-Transformer)
SOTA
Taming Transformers for High-Resolution Image Synthesis arXiv:2012.09841