StackGAN + VICTR

Reported on 4 benchmarks across 4 tasks · 1 paper

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

Audio2 results

10-shot image generationonCOCO (Common Objects in Context)
Inception score· 2020-10-07
10.38
best: 34.67 (FuseDream (k=10, 256))
VICTR: Visual Information Captured Text Representation for Text-to-Image Multimodal Tasks arXiv:2010.03182
1 Image, 2*2 StitchionCOCO (Common Objects in Context)
Inception score· 2020-10-07
10.38
best: 34.67 (FuseDream (k=10, 256))
VICTR: Visual Information Captured Text Representation for Text-to-Image Multimodal Tasks arXiv:2010.03182

Medical1 result

Image GenerationonCOCO (Common Objects in Context)
Inception score· 2020-10-07
10.38
best: 34.67 (FuseDream (k=10, 256))
VICTR: Visual Information Captured Text Representation for Text-to-Image Multimodal Tasks arXiv:2010.03182

Natural Language Processing1 result

Text-to-Image GenerationonCOCO (Common Objects in Context)
Inception score· 2020-10-07
10.38
best: 34.67 (FuseDream (k=10, 256))
VICTR: Visual Information Captured Text Representation for Text-to-Image Multimodal Tasks arXiv:2010.03182