HyperAI초신경

홈 뉴스 최신 연구 논문 튜토리얼 데이터셋 백과사전 SOTA LLM 모델 GPU 랭킹 컨퍼런스

한국어

HyperAI초신경

Anomaly Classification On Goodsad

평가 지표

AUPR

AUROC

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	AUPR	AUROC	Paper Title	Repository
PatchCore-100%	86.1	85.5	Towards Total Recall in Industrial Anomaly Detection
PatchCore-1%	83.3	81.4	Towards Total Recall in Industrial Anomaly Detection
SimpleNet	78.7	75.3	SimpleNet: A Simple Network for Image Anomaly Detection and Localization
RD4AD	68.2	66.5	Anomaly Detection via Reverse Distillation from One-Class Embedding
DRAEM	71	65.9	DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detection
SPADE	68.7	64.1	Sub-Image Anomaly Detection with Deep Pyramid Correspondences
NSA	71.8	67.3	Natural Synthetic Anomalies for Self-Supervised Anomaly Detection and Localization
CFLOW-AD	75.3	71.2	CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flows
MiniMaxAD-fr	-	86.1	MiniMaxAD: A Lightweight Autoencoder for Feature-Rich Anomaly Detection	-
CutPaste	62.8	60.2	CutPaste: Self-Supervised Learning for Anomaly Detection and Localization
f-AnoGAN	66.6	62.8	f-AnoGAN: Fast Unsupervised Anomaly Detection with Generative Adversarial Networks

0 of 11 row(s) selected.