HyperAI超神经

Out Of Distribution Detection On Imagenet 1K 12

评估指标

AUROC

FPR95

评测结果

各个模型在此基准测试上的表现结果

			Paper Title
RP+GradNorm	-	70.12	Detecting Out-of-distribution Data through In-distribution Class Prior
DOE	83.54	59.83	Out-of-distribution Detection with Implicit Outlier Transformation
DML	-	54.74	Decoupling MaxLogit for Out-of-Distribution Detection
ODIN+UMAP (ResNet-50)	89.24	40.94	Unleashing Mask: Explore the Intrinsic Out-of-Distribution Detection Capability
MOS (BiT-S-R101x1)	90.11	39.97	MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Space
MCM (CLIP-L)	91.49	38.17	Delving into Out-of-Distribution Detection with Vision-Language Representations
NPOS	91.22	37.93	Non-Parametric Outlier Synthesis
RankFeat (ResNetv2-101)	92.15	36.8	RankFeat: Rank-1 Feature Removal for Out-of-distribution Detection
DICE + ReAct (ResNet-50)	93.4	27.25	DICE: Leveraging Sparsification for Out-of-Distribution Detection
BATS (ResNet-50)	94.28	27.11	Boosting Out-of-distribution Detection with Typical Features
ASH-S (ResNet-50)	95.12	22.8	Extremely Simple Activation Shaping for Out-of-Distribution Detection
LINe (ResNet-50)	95.03	20.70	LINe: Out-of-Distribution Detection by Leveraging Important Neurons
SCALE (ResNet50)	95.71	20.05	Scaling for Training Time and Post-hoc Out-of-distribution Detection Enhancement
NNGuide (ResNet50 w/ ReAct)	95.45	19.72	Nearest Neighbor Guidance for Out-of-Distribution Detection
NNGuide (RegNet)	95.42	17.97	Nearest Neighbor Guidance for Out-of-Distribution Detection
MOOD	89.1	-	Rethinking Out-of-distribution (OOD) Detection: Masked Image Modeling is All You Need

0 of 16 row(s) selected.

HyperAI超神经

Out Of Distribution Detection On Imagenet 1K 12

评估指标

AUROC

FPR95

评测结果

各个模型在此基准测试上的表现结果

			Paper Title
RP+GradNorm	-	70.12	Detecting Out-of-distribution Data through In-distribution Class Prior
DOE	83.54	59.83	Out-of-distribution Detection with Implicit Outlier Transformation
DML	-	54.74	Decoupling MaxLogit for Out-of-Distribution Detection
ODIN+UMAP (ResNet-50)	89.24	40.94	Unleashing Mask: Explore the Intrinsic Out-of-Distribution Detection Capability
MOS (BiT-S-R101x1)	90.11	39.97	MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Space
MCM (CLIP-L)	91.49	38.17	Delving into Out-of-Distribution Detection with Vision-Language Representations
NPOS	91.22	37.93	Non-Parametric Outlier Synthesis
RankFeat (ResNetv2-101)	92.15	36.8	RankFeat: Rank-1 Feature Removal for Out-of-distribution Detection
DICE + ReAct (ResNet-50)	93.4	27.25	DICE: Leveraging Sparsification for Out-of-Distribution Detection
BATS (ResNet-50)	94.28	27.11	Boosting Out-of-distribution Detection with Typical Features
ASH-S (ResNet-50)	95.12	22.8	Extremely Simple Activation Shaping for Out-of-Distribution Detection
LINe (ResNet-50)	95.03	20.70	LINe: Out-of-Distribution Detection by Leveraging Important Neurons
SCALE (ResNet50)	95.71	20.05	Scaling for Training Time and Post-hoc Out-of-distribution Detection Enhancement
NNGuide (ResNet50 w/ ReAct)	95.45	19.72	Nearest Neighbor Guidance for Out-of-Distribution Detection
NNGuide (RegNet)	95.42	17.97	Nearest Neighbor Guidance for Out-of-Distribution Detection
MOOD	89.1	-	Rethinking Out-of-distribution (OOD) Detection: Masked Image Modeling is All You Need

0 of 16 row(s) selected.