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· 2022-03-03
12.33
best: 9.8 (Contextual RQ-Transformer)
SOTA
Autoregressive Image Generation using Residual Quantization arXiv:2203.01941
Image GenerationonImageNet 256x256
FID· 2022-03-03
3.83
best: 1.06 (SiT-XL/2 + UCGM-S (E2E-VAE + 40 sampling steps + CFG))
Autoregressive Image Generation using Residual Quantization arXiv:2203.01941

Audio2 results

10-shot image generationonConceptual Captions
FID· 2022-03-03
12.33
best: 9.8 (Contextual RQ-Transformer)
SOTA
Autoregressive Image Generation using Residual Quantization arXiv:2203.01941
1 Image, 2*2 StitchionConceptual Captions
FID· 2022-03-03
12.33
best: 9.8 (Contextual RQ-Transformer)
SOTA
Autoregressive Image Generation using Residual Quantization arXiv:2203.01941

Natural Language Processing1 result

Text-to-Image GenerationonConceptual Captions
FID· 2022-03-03
12.33
best: 9.8 (Contextual RQ-Transformer)
SOTA
Autoregressive Image Generation using Residual Quantization arXiv:2203.01941