Contextual RQ-Transformer

Reported on 5 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.

Medical2 results

Image GenerationonConceptual Captions
FID· 2022-06-09
9.8
SOTA
Draft-and-Revise: Effective Image Generation with Contextual RQ-Transformer arXiv:2206.04452
Image GenerationonImageNet 256x256
FID· 2022-06-09
3.41
best: 1.06 (SiT-XL/2 + UCGM-S (E2E-VAE + 40 sampling steps + CFG))
Draft-and-Revise: Effective Image Generation with Contextual RQ-Transformer arXiv:2206.04452

Audio2 results

10-shot image generationonConceptual Captions
FID· 2022-06-09
9.8
SOTA
Draft-and-Revise: Effective Image Generation with Contextual RQ-Transformer arXiv:2206.04452
1 Image, 2*2 StitchionConceptual Captions
FID· 2022-06-09
9.8
SOTA
Draft-and-Revise: Effective Image Generation with Contextual RQ-Transformer arXiv:2206.04452

Natural Language Processing1 result

Text-to-Image GenerationonConceptual Captions
FID· 2022-06-09
9.8
SOTA
Draft-and-Revise: Effective Image Generation with Contextual RQ-Transformer arXiv:2206.04452