VAE

Reported on 18 benchmarks across 3 tasks · 2 papers · 17 SOTA

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

Computer Vision14 results

Image ClusteringonImageNet-10
Accuracy· 2013-12-20
0.334
best: 0.992 (TAC)
SOTA
Auto-Encoding Variational Bayes arXiv:1312.6114
Image ClusteringonImageNet-10
NMI· 2013-12-20
0.193
best: 0.985 (TAC)
SOTA
Auto-Encoding Variational Bayes arXiv:1312.6114
Image ClusteringonCIFAR-10
ARI· uses extra data· 2013-12-20
0.168
best: 0.989 (TURTLE (CLIP + DINOv2))
SOTA
Auto-Encoding Variational Bayes arXiv:1312.6114
Image ClusteringonCIFAR-10
Accuracy· uses extra data· 2013-12-20
0.291
best: 0.995 (TURTLE (CLIP + DINOv2))
SOTA
Auto-Encoding Variational Bayes arXiv:1312.6114
Image ClusteringonCIFAR-10
NMI· uses extra data· 2013-12-20
0.245
best: 0.985 (TURTLE (CLIP + DINOv2))
SOTA
Auto-Encoding Variational Bayes arXiv:1312.6114
Image ClusteringonTiny-ImageNet
Accuracy· 2013-12-20
0.036
best: 0.698 (PRO-DSC)
SOTA
Auto-Encoding Variational Bayes arXiv:1312.6114
Image ClusteringonTiny-ImageNet
NMI· 2013-12-20
0.113
best: 0.8178 (ITAE)
SOTA
Auto-Encoding Variational Bayes arXiv:1312.6114
Image ClusteringonCIFAR-100
Accuracy· uses extra data· 2013-12-20
0.152
best: 0.898 (TURTLE (CLIP + DINOv2))
SOTA
Auto-Encoding Variational Bayes arXiv:1312.6114
Image ClusteringonCIFAR-100
NMI· uses extra data· 2013-12-20
0.108
best: 0.915 (TURTLE (CLIP + DINOv2))
SOTA
Auto-Encoding Variational Bayes arXiv:1312.6114
Image ClusteringonSTL-10
Accuracy· uses extra data· 2013-12-20
0.282
best: 0.997 (TURTLE (CLIP + DINOv2))
SOTA
Auto-Encoding Variational Bayes arXiv:1312.6114
Image ClusteringonSTL-10
NMI· uses extra data· 2013-12-20
0.2
best: 0.993 (TURTLE (CLIP + DINOv2))
SOTA
Auto-Encoding Variational Bayes arXiv:1312.6114
Image ClusteringonImagenet-dog-15
Accuracy· 2013-12-20
0.179
best: 0.943 (MAE-CT (best))
SOTA
Auto-Encoding Variational Bayes arXiv:1312.6114
Image ClusteringonImagenet-dog-15
NMI· 2013-12-20
0.107
best: 0.904 (MAE-CT (best))
SOTA
Auto-Encoding Variational Bayes arXiv:1312.6114
Image ClassificationonVTAB-1k
Top-1 Accuracy· uses extra data· 2019-10-01
37.5
best: 79.99 (ALIGN (50 hypers/task))
A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark arXiv:1910.04867

Methodology4 results

Anomaly DetectiononMVTec LOCO AD
Avg. Detection AUROC· 2013-12-20
54.3
best: 95.3 (CSAD)
SOTA
Auto-Encoding Variational Bayes arXiv:1312.6114
Anomaly DetectiononMVTec LOCO AD
Detection AUROC (only logical)· 2013-12-20
53.8
best: 98.1 (PSAD)
SOTA
Auto-Encoding Variational Bayes arXiv:1312.6114
Anomaly DetectiononMVTec LOCO AD
Detection AUROC (only structural)· 2013-12-20
54.8
best: 95.9 (PUAD-M)
SOTA
Auto-Encoding Variational Bayes arXiv:1312.6114
Anomaly DetectiononMVTec LOCO AD
Segmentation AU-sPRO (until FPR 5%)· 2013-12-20
38.2
best: 83.2 (SAM-LAD)
SOTA
Auto-Encoding Variational Bayes arXiv:1312.6114