HyperAI超神经

首页算力平台文档资讯论文教程数据集百科 SOTA LLM 模型天梯 GPU 天梯顶会

中文

HyperAI超神经

Anomaly Detection On One Class Cifar 100

评估指标

AUROC

评测结果

各个模型在此基准测试上的表现结果

		Paper Title	Repository
GeneralAD	98.4	GeneralAD: Anomaly Detection Across Domains by Attending to Distorted Features
Transformaly	97.7	Transformaly -- Two (Feature Spaces) Are Better Than One
PANDA-OE	97.3	PANDA: Adapting Pretrained Features for Anomaly Detection and Segmentation
Mean-Shifted Contrastive Loss	96.5	Mean-Shifted Contrastive Loss for Anomaly Detection
PANDA	94.1	PANDA: Adapting Pretrained Features for Anomaly Detection and Segmentation
CSI	89.6	CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances
GAN based Anomaly Detection in Imbalance Problems	87.4	GAN-based Anomaly Detection in Imbalance Problems	-
DisAug CLR	86.5	Learning and Evaluating Representations for Deep One-class Classification
DUIAD	86	Deep Unsupervised Image Anomaly Detection: An Information Theoretic Framework	-
Rotation Prediction	84.1	Learning and Evaluating Representations for Deep One-class Classification
MTL	83.95	Shifting Transformation Learning for Out-of-Distribution Detection	-
Self-Supervised Multi-Head RotNet	80.1	PANDA: Adapting Pretrained Features for Anomaly Detection and Segmentation
Geom	78.7	Deep Anomaly Detection Using Geometric Transformations
Self-Supervised DeepSVDD	67	PANDA: Adapting Pretrained Features for Anomaly Detection and Segmentation
Self-Supervised One-class SVM, RBF kernel	62.6	PANDA: Adapting Pretrained Features for Anomaly Detection and Segmentation

0 of 15 row(s) selected.

Anomaly Detection On One Class Cifar 100 | SOTA | HyperAI超神经