FCE

Reported on 5 benchmarks across 3 tasks · 1 paper

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

Computer Vision4 results

Image ClassificationonSVHN, 500 Labels
Accuracy· 2019-12-02
95.53
best: 96.39 (Triple-GAN-V2 (CNN-13))
Flow Contrastive Estimation of Energy-Based Models arXiv:1912.00589
Image ClassificationonSVHN, 1000 labels
Accuracy· 2019-12-02
96.13
best: 97.58 (EnAET)
Flow Contrastive Estimation of Energy-Based Models arXiv:1912.00589
Semi-Supervised Image ClassificationonSVHN, 500 Labels
Accuracy· 2019-12-02
95.53
best: 96.39 (Triple-GAN-V2 (CNN-13))
Flow Contrastive Estimation of Energy-Based Models arXiv:1912.00589
Semi-Supervised Image ClassificationonSVHN, 1000 labels
Accuracy· 2019-12-02
96.13
best: 97.58 (EnAET)
Flow Contrastive Estimation of Energy-Based Models arXiv:1912.00589

Medical1 result

Image GenerationonCelebA 64x64
FID· 2019-12-02
12.21
best: 1.27 (DDPM-IP)
Flow Contrastive Estimation of Energy-Based Models arXiv:1912.00589