HyperAI超神経

ホームプラットフォームドキュメントニュース論文チュートリアルデータセット百科事典 SOTA LLMモデル GPU ランキング学会

サイトについて

日本語

HyperAI超神経

Anomaly Detection On One Class Imagenet 30

評価指標

AUROC

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

		Paper Title	Repository
BCE-Clip (OE)	99.90	Exposing Outlier Exposure: What Can Be Learned From Few, One, and Zero Outlier Images
CLIP (Zero Shot)	99.88	Exposing Outlier Exposure: What Can Be Learned From Few, One, and Zero Outlier Images
Binary Cross Entropy (OE)	97.7	Exposing Outlier Exposure: What Can Be Learned From Few, One, and Zero Outlier Images
CSI	91.6	CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances
FCDD	91	Explainable Deep One-Class Classification
RotNet + Translation + Self-Attention + Resize	85.7	Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty
RotNet + Translation + Self-Attention	84.8	Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty
RotNet + Self-Attention	81.6	Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty
RotNet + Translation	77.9	Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty
RotNet	65.3	Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty
Supervised (OE)	56.1	Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty

0 of 11 row(s) selected.