Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/DM-GAN

DM-GAN

Reported on 28 benchmarks across 4 tasks · 1 paper · 20 SOTA

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

Audio14 results

10-shot image generationonCOCO (Common Objects in Context)
FID· 2019-04-02
32.64
best: 5 (RAT-Diffusion)
SOTA
DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis arXiv:1904.01310
10-shot image generationonCOCO (Common Objects in Context)
Inception score· 2019-04-02
30.49
best: 34.67 (FuseDream (k=10, 256))
SOTA
DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis arXiv:1904.01310
10-shot image generationonCOCO (Common Objects in Context)
SOA-C· 2019-04-02
33.44
best: 61.09 (Lafite)
SOTA
DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis arXiv:1904.01310
10-shot image generationonMulti-Modal-CelebA-HQ
Acc· 2019-04-02
16.4
best: 20.4 (TediGAN-B )
SOTA
DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis arXiv:1904.01310
10-shot image generationonMulti-Modal-CelebA-HQ
Real· 2019-04-02
16.9
best: 22.6 (TediGAN-A)
SOTA
DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis arXiv:1904.01310
1 Image, 2*2 StitchionCOCO (Common Objects in Context)
FID· 2019-04-02
32.64
best: 5 (RAT-Diffusion)
SOTA
DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis arXiv:1904.01310
1 Image, 2*2 StitchionCOCO (Common Objects in Context)
Inception score· 2019-04-02
30.49
best: 34.67 (FuseDream (k=10, 256))
SOTA
DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis arXiv:1904.01310
1 Image, 2*2 StitchionCOCO (Common Objects in Context)
SOA-C· 2019-04-02
33.44
best: 61.09 (Lafite)
SOTA
DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis arXiv:1904.01310
1 Image, 2*2 StitchionMulti-Modal-CelebA-HQ
Acc· 2019-04-02
16.4
best: 20.4 (TediGAN-B )
SOTA
DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis arXiv:1904.01310
1 Image, 2*2 StitchionMulti-Modal-CelebA-HQ
Real· 2019-04-02
16.9
best: 22.6 (TediGAN-A)
SOTA
DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis arXiv:1904.01310
10-shot image generationonMulti-Modal-CelebA-HQ
FID· 2019-04-02
131.05
best: 10.31 (Swinv2-Imagen)
DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis arXiv:1904.01310
10-shot image generationonMulti-Modal-CelebA-HQ
LPIPS· 2019-04-02
0.544
best: 0.456 (TediGAN-A)
DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis arXiv:1904.01310
1 Image, 2*2 StitchionMulti-Modal-CelebA-HQ
FID· 2019-04-02
131.05
best: 10.31 (Swinv2-Imagen)
DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis arXiv:1904.01310
1 Image, 2*2 StitchionMulti-Modal-CelebA-HQ
LPIPS· 2019-04-02
0.544
best: 0.456 (TediGAN-A)
DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis arXiv:1904.01310

Medical7 results

Image GenerationonCOCO (Common Objects in Context)
FID· 2019-04-02
32.64
best: 5 (RAT-Diffusion)
SOTA
DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis arXiv:1904.01310
Image GenerationonCOCO (Common Objects in Context)
Inception score· 2019-04-02
30.49
best: 34.67 (FuseDream (k=10, 256))
SOTA
DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis arXiv:1904.01310
Image GenerationonCOCO (Common Objects in Context)
SOA-C· 2019-04-02
33.44
best: 61.09 (Lafite)
SOTA
DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis arXiv:1904.01310
Image GenerationonMulti-Modal-CelebA-HQ
Acc· 2019-04-02
16.4
best: 20.4 (TediGAN-B )
SOTA
DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis arXiv:1904.01310
Image GenerationonMulti-Modal-CelebA-HQ
Real· 2019-04-02
16.9
best: 22.6 (TediGAN-A)
SOTA
DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis arXiv:1904.01310
Image GenerationonMulti-Modal-CelebA-HQ
FID· 2019-04-02
131.05
best: 10.31 (Swinv2-Imagen)
DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis arXiv:1904.01310
Image GenerationonMulti-Modal-CelebA-HQ
LPIPS· 2019-04-02
0.544
best: 0.456 (TediGAN-A)
DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis arXiv:1904.01310

Natural Language Processing7 results

Text-to-Image GenerationonCOCO (Common Objects in Context)
FID· 2019-04-02
32.64
best: 5 (RAT-Diffusion)
SOTA
DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis arXiv:1904.01310
Text-to-Image GenerationonCOCO (Common Objects in Context)
Inception score· 2019-04-02
30.49
best: 34.67 (FuseDream (k=10, 256))
SOTA
DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis arXiv:1904.01310
Text-to-Image GenerationonCOCO (Common Objects in Context)
SOA-C· 2019-04-02
33.44
best: 61.09 (Lafite)
SOTA
DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis arXiv:1904.01310
Text-to-Image GenerationonMulti-Modal-CelebA-HQ
Acc· 2019-04-02
16.4
best: 20.4 (TediGAN-B )
SOTA
DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis arXiv:1904.01310
Text-to-Image GenerationonMulti-Modal-CelebA-HQ
Real· 2019-04-02
16.9
best: 22.6 (TediGAN-A)
SOTA
DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis arXiv:1904.01310
Text-to-Image GenerationonMulti-Modal-CelebA-HQ
FID· 2019-04-02
131.05
best: 10.31 (Swinv2-Imagen)
DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis arXiv:1904.01310
Text-to-Image GenerationonMulti-Modal-CelebA-HQ
LPIPS· 2019-04-02
0.544
best: 0.456 (TediGAN-A)
DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis arXiv:1904.01310