Papers with Code · CC BY-SA 4.0

MVTec AD

아카이브 평가 148건 · 마지막 적재/변경 2026-10-30

평가 기록

과거 수집 기록이며 최신 순위가 아닙니다. 데이터셋 버전·split·실험 조건과 지표 방향이 검증되지 않은 결과는 직접 비교할 수 없습니다. 날짜는 논문 날짜이며 최신 평가일을 뜻하지 않습니다.

표가 화면보다 넓으면 좌우로 스크롤하여 논문과 구현 링크를 확인하세요.

원본 기록 순서 · 순위 미부여
모델	원본 지표·값	논문	구현
GLASS	Detection AUROC 99.9 Segmentation AUROC 99.3 Segmentation AUPRO 96.8	A Unified Anomaly Synthesis Strategy with Gradient Ascent for Industrial Anomaly Detection and Localization 2024-07-12	코드 1 · 코드 2
UniNet	Detection AUROC 99.90 Segmentation AUROC 98.81 Segmentation AUPRO 96.00	UniNet: A Contrastive Learning-guided Unified Framework with Feature Selection for Anomaly Detection 2025-02-28	코드 1
PBAS	Detection AUROC 99.8 Segmentation AUROC 98.6 Segmentation AUPRO 97.3	Progressive Boundary Guided Anomaly Synthesis for Industrial Anomaly Detection 2024-12-23	코드 1
HETMM	Detection AUROC 99.8 Segmentation AUROC 99 Segmentation AUPRO 96.4	Hard-normal Example-aware Template Mutual Matching for Industrial Anomaly Detection 2023-03-28	코드 1
INP-Fomer ViT-L (model-unified multi-class)	Detection AUROC 99.8 Segmentation AUROC 98.6 Segmentation AUPRO 95.6 Segmentation AP 72.1	Exploring Intrinsic Normal Prototypes within a Single Image for Universal Anomaly Detection 2025-03-04	코드 1 · 코드 2
DDAD	Detection AUROC 99.8 Segmentation AUROC 98.1	Anomaly Detection with Conditioned Denoising Diffusion Models 2023-05-25	코드 1
EfficientAD (early stopping)	Detection AUROC 99.8 FPS 269	EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latencies 2023-03-25	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 · 코드 7 · 코드 8 · 코드 9 · 코드 10 · 코드 11 · 코드 12 · 코드 13 · 코드 14 · 코드 15 · 코드 16 · 코드 17 · 코드 18 · 코드 19 · 코드 20 · 코드 21 · 코드 22 · 코드 23 · 코드 24 · 코드 25 · 코드 26 · 코드 27 · 코드 28 · 코드 29 · 코드 30 · 코드 31 · 코드 32 · 코드 33
Dinomaly ViT-L (model-unified multi-class)	Detection AUROC 99.77 Segmentation AUROC 98.54 Segmentation AUPRO 95.09 Segmentation AP 70.53	Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detection 2024-05-23	코드 1 · 코드 2
ReConPatch Ensemble (+RefineNet)	Detection AUROC 99.72 Segmentation AUROC 99.2	ReConPatch : Contrastive Patch Representation Learning for Industrial Anomaly Detection 2023-05-26	코드 1
ReConPatch WRN-50 (+RefineNet)	Detection AUROC 99.71 Segmentation AUROC 98.62	ReConPatch : Contrastive Patch Representation Learning for Industrial Anomaly Detection 2023-05-26	코드 1
ADClick	Detection AUROC 99.7 Segmentation AUROC 99.2 Segmentation AUPRO 97.8 Segmentation AP 82.9	Towards Efficient Pixel Labeling for Industrial Anomaly Detection and Localization 2024-07-03	연결 없음
CPR	Detection AUROC 99.7 Segmentation AUROC 99.2 Segmentation AUPRO 97.8 Segmentation AP 82.7 FPS 113	Target before Shooting: Accurate Anomaly Detection and Localization under One Millisecond via Cascade Patch Retrieval 2023-08-13	코드 1
CPR-fast	Detection AUROC 99.7 Segmentation AUROC 99.2 Segmentation AUPRO 97.7 Segmentation AP 82.3 FPS 245	Target before Shooting: Accurate Anomaly Detection and Localization under One Millisecond via Cascade Patch Retrieval 2023-08-13	코드 1
MSFlow	Detection AUROC 99.7 Segmentation AUROC 98.8 Segmentation AUPRO 97.1	MSFlow: Multi-Scale Flow-based Framework for Unsupervised Anomaly Detection 2023-08-29	코드 1
CRAS	Detection AUROC 99.7 Segmentation AUROC 98.4	Center-aware Residual Anomaly Synthesis for Multi-class Industrial Anomaly Detection 2025-05-23	코드 1
PNI Ensemble	Detection AUROC 99.63 Segmentation AUROC 99.06 Segmentation AUPRO 96.55	PNI : Industrial Anomaly Detection using Position and Neighborhood Information 2022-11-22	코드 1
ReConPatch WRN-101	Detection AUROC 99.62 Segmentation AUROC 98.53	ReConPatch : Contrastive Patch Representation Learning for Industrial Anomaly Detection 2023-05-26	코드 1
WeakREST-Un	Detection AUROC 99.6 Segmentation AUROC 99.3 Segmentation AUPRO 97.6 Segmentation AP 83.0 FPS 25.2	Industrial Anomaly Detection and Localization Using Weakly-Supervised Residual Transformers 2023-06-06	연결 없음
Dinomaly ViT-B (model-unified multi-class)	Detection AUROC 99.60 Segmentation AUROC 98.35 Segmentation AUPRO 94.79 Segmentation AP 69.29	Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detection 2024-05-23	코드 1 · 코드 2
PatchCore Large	Detection AUROC 99.6 Segmentation AUROC 98.2 Segmentation AUPRO 93.5 FPS 5.88	Towards Total Recall in Industrial Anomaly Detection 2021-06-15	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 · 코드 7 · 코드 8 · 코드 9 · 코드 10 · 코드 11 · 코드 12 · 코드 13 · 코드 14 · 코드 15 · 코드 16 · 코드 17 · 코드 18
RealNet	Detection AUROC 99.6 Segmentation AUROC 99.0 Segmentation AUPRO 93.0	RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detection 2024-03-09	코드 1
RememberingNormality	Detection AUROC 99.6 Segmentation AUROC 98.2	Remembering Normality: Memory-guided Knowledge Distillation for Unsupervised Anomaly Detection 2023-01-01	코드 1 · 코드 2
SimpleNet	Detection AUROC 99.6 Segmentation AUROC 98.1 FPS 77(FP32 on 3080ti)	SimpleNet: A Simple Network for Image Anomaly Detection and Localization 2023-03-27	코드 1 · 코드 2
PNI	Detection AUROC 99.56 Segmentation AUROC 98.98 Segmentation AUPRO 96.05	PNI : Industrial Anomaly Detection using Position and Neighborhood Information 2022-11-22	코드 1
MemSeg	Detection AUROC 99.56 Segmentation AUROC 98.84 FPS 31.3	MemSeg: A semi-supervised method for image surface defect detection using differences and commonalities 2022-05-02	코드 1 · 코드 2 · 코드 3 · 코드 4
ReConPatch WRN-50	Detection AUROC 99.56 Segmentation AUROC 98.18	ReConPatch : Contrastive Patch Representation Learning for Industrial Anomaly Detection 2023-05-26	코드 1
ReContrast	Detection AUROC 99.5 Segmentation AUROC 98.4 Segmentation AUPRO 95.2	연결 없음 논문 날짜 미기재	연결 없음
AnomalyDINO-S (full-shot)	Detection AUROC 99.5 Segmentation AUROC 98.2 Segmentation AUPRO 95	AnomalyDINO: Boosting Patch-based Few-shot Anomaly Detection with DINOv2 2024-05-23	코드 1
POUTA	Detection AUROC 99.5 Segmentation AUROC 98.8	Produce Once, Utilize Twice for Anomaly Detection 2023-12-20	연결 없음
DMAD	Detection AUROC 99.5 Segmentation AUROC 98.2	Diversity-Measurable Anomaly Detection 2023-03-09	코드 1