HyperAIHyperAI超神经
首页资讯论文教程数据集百科SOTALLM 模型天梯GPU 天梯顶会
全站搜索
关于
HyperAIHyperAI超神经

Anomaly Detection On One Class Imagenet 30

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

模型名称
AUROC
Paper TitleRepository
RotNet + Translation77.9Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty-
RotNet + Translation + Self-Attention84.8Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty-
RotNet65.3Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty-
CSI91.6CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances-
RotNet + Translation + Self-Attention + Resize85.7Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty-
FCDD91Explainable Deep One-Class Classification-
CLIP (Zero Shot)99.88Exposing Outlier Exposure: What Can Be Learned From Few, One, and Zero Outlier Images-
BCE-Clip (OE)99.90Exposing Outlier Exposure: What Can Be Learned From Few, One, and Zero Outlier Images-
RotNet + Self-Attention81.6Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty-
Supervised (OE)56.1Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty-
Binary Cross Entropy (OE)97.7Exposing Outlier Exposure: What Can Be Learned From Few, One, and Zero Outlier Images-
0 of 11 row(s) selected.
Anomaly Detection On One Class Imagenet 30 | SOTA | HyperAI超神经