Anomaly Detection on MNIST

Metric: ROC AUC (higher is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

Hide augmentations

Sort:

#	Model↕	ROC AUC▼	Augmentations	Paper	Date↕	Code
1	GAN-based Anomaly Detection in Imbalance Problems	99.7	Yes	-	-	-
2	IGD (pre-trained ImageNet)	99.27	Yes	Deep One-Class Classification via Interpolated G...	2021-01-25	Code
3	IGD (scratch)	98.69	Yes	Deep One-Class Classification via Interpolated G...	2021-01-25	Code
4	DASVDD	97.7	Yes	DASVDD: Deep Autoencoding Support Vector Data De...	2021-06-09	Code
5	LIS-AE	97.68	Yes	Latent-Insensitive autoencoders for Anomaly Dete...	2021-10-25	-
6	P-KDGAN	97.25	Yes	P-KDGAN: Progressive Knowledge Distillation with...	2020-07-14	-

#1GAN-based Anomaly Detection in Imbalance Problems
99.7
ROC AUC· Augmentations
No paper
#2IGD (pre-trained ImageNet)SOTA
99.27
ROC AUC· Augmentations· 2021-01-25
Deep One-Class Classification via Interpolated Gaussian Descriptor Code
#3IGD (scratch)
98.69
ROC AUC· Augmentations· 2021-01-25
Deep One-Class Classification via Interpolated Gaussian Descriptor Code
#4DASVDD
97.7
ROC AUC· Augmentations· 2021-06-09
DASVDD: Deep Autoencoding Support Vector Data Descriptor for Anomaly Detection Code
#5LIS-AE
97.68
ROC AUC· Augmentations· 2021-10-25
Latent-Insensitive autoencoders for Anomaly Detection
#6P-KDGANSOTA
97.25
ROC AUC· Augmentations· 2020-07-14
P-KDGAN: Progressive Knowledge Distillation with GANs for One-class Novelty Detection