Pith. sign in

Vector quantized diffusion model for text- to-image synthesis

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.CV 1

years

2024 1

verdicts

CONDITIONAL 1

roles

background 1

polarities

background 1

representative citing papers

Text-to-Image GAN with Pretrained Representations

cs.CV · 2024-12-30 · conditional · novelty 6.0

TIGER, a text-to-image GAN that stacks CLIP and DINO representations in the discriminator, reports FID 5.48 on COCO and 9.38 on CUB, surpassing prior GAN and some diffusion baselines.

citing papers explorer

Showing 1 of 1 citing paper.

  • Text-to-Image GAN with Pretrained Representations cs.CV · 2024-12-30 · conditional · none · ref 7

    TIGER, a text-to-image GAN that stacks CLIP and DINO representations in the discriminator, reports FID 5.48 on COCO and 9.38 on CUB, surpassing prior GAN and some diffusion baselines.