Out Of Distribution Detection On Imagenet 1K 9

평가 지표

AUROC

FPR95

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	AUROC	FPR95	Paper Title	Repository
DICE (ResNet-50)	87.48	46.49	DICE: Leveraging Sparsification for Out-of-Distribution Detection
SCALE (ResNet50)	92.26	34.51	Scaling for Training Time and Post-hoc Out-of-distribution Detection Enhancement	-
LINe (ResNet50)	92.85	28.52	LINe: Out-of-Distribution Detection by Leveraging Important Neurons
RankFeat (ResNetv2-101)	90.93	39.34	RankFeat: Rank-1 Feature Removal for Out-of-distribution Detection
DML	-	61.43	Decoupling MaxLogit for Out-of-Distribution Detection	-
GradNorm (ResNetv2-101)	-	60.86	On the Importance of Gradients for Detecting Distributional Shifts in the Wild
SHE	-	45.35	Out-of-Distribution Detection based on In-Distribution Data Patterns Memorization with Modern Hopfield Energy
ASH-S (ResNet-50)	90.98	39.78	Extremely Simple Activation Shaping for Out-of-Distribution Detection
MCM (CLIP-L)	92.00	35.42	Delving into Out-of-Distribution Detection with Vision-Language Representations
KNN (ResNet-50)	74.87	77.09	Out-of-Distribution Detection with Deep Nearest Neighbors
ODIN+UMAP (ResNet-50)	86.99	50.06	Unleashing Mask: Explore the Intrinsic Out-of-Distribution Detection Capability
MOOD	88.5	-	Rethinking Out-of-distribution (OOD) Detection: Masked Image Modeling is All You Need
BATS (ResNet-50)	91.83	34.34	Boosting Out-of-distribution Detection with Typical Features	-
ReAct (ResNet-50)	86.64	51.56	ReAct: Out-of-distribution Detection With Rectified Activations
MCM (CLIP-B)	89.77	44.69	Delving into Out-of-Distribution Detection with Vision-Language Representations
Watermarking (WRN-40-2 w/ Energy)	79.85	71.85	Watermarking for Out-of-distribution Detection
Watermarking (WRN-40-2 w/ MSP)	82.03	70.59	Watermarking for Out-of-distribution Detection
RP+GradNorm	-	83.29	Detecting Out-of-distribution Data through In-distribution Class Prior
KNN (ResNet-50 SupCon)	84.62	60.02	Out-of-Distribution Detection with Deep Nearest Neighbors
DOE	83.05	67.84	Out-of-distribution Detection with Implicit Outlier Transformation

0 of 24 row(s) selected.