partGAN

Reported on 3 benchmarks across 1 task · 1 paper

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

Adversarial3 results

Text GenerationonCOCO Captions
BLEU-2· 2017-09-24
0.91
best: 2 (tecpic)
Long Text Generation via Adversarial Training with Leaked Information arXiv:1709.08624
Text GenerationonCOCO Captions
BLEU-3· 2017-09-24
0.713
best: 0.88 (LeakGAN)
Long Text Generation via Adversarial Training with Leaked Information arXiv:1709.08624
Text GenerationonCOCO Captions
BLEU-5· 2017-09-24
0.59
best: 0.686 (LeakGAN)
Long Text Generation via Adversarial Training with Leaked Information arXiv:1709.08624