Out Of Distribution Detection On Imagenet 1K 10

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

模型名称
AUROC
FPR95
Paper TitleRepository
DICE + ReAct (ResNet-50)92.7428.07DICE: Leveraging Sparsification for Out-of-Distribution Detection-
GradNorm (ResNetv2-101)-61.42On the Importance of Gradients for Detecting Distributional Shifts in the Wild-
LINe (ResNet-50)94.4422.54LINe: Out-of-Distribution Detection by Leveraging Important Neurons-
Watermarking (WRN-40-2 w/ MSP)84.0061.2Watermarking for Out-of-distribution Detection-
Watermarking (WRN-40-2 w/ Energy)80.8067.75Watermarking for Out-of-distribution Detection-
MOS (BiT-S-R101x1)81.2360.43MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Space-
ViM (ViT-B/16)95.3420.31ViM: Out-Of-Distribution with Virtual-logit Matching-
ODIN+UMAP (ResNet-50)88.3542.02Unleashing Mask: Explore the Intrinsic Out-of-Distribution Detection Capability-
DOE88.934.67Out-of-distribution Detection with Implicit Outlier Transformation-
GEN-77.93GEN: Pushing the Limits of Softmax-Based Out-of-Distribution Detection
ViM (BiT-S-R101×1)-4.69ViM: Out-Of-Distribution with Virtual-logit Matching-
NAC-UE (ResNet-50)97.9-Neuron Activation Coverage: Rethinking Out-of-distribution Detection and Generalization-
BATS (ResNet-50)92.2738.9Boosting Out-of-distribution Detection with Typical Features-
SSD85.457.2SSD: A Unified Framework for Self-Supervised Outlier Detection-
KNN (ResNet-50 SupCon)94.4516.97Out-of-Distribution Detection with Deep Nearest Neighbors-
NNGuide (RegNet)95.8217.00Nearest Neighbor Guidance for Out-of-Distribution Detection-
MOOD91.3-Rethinking Out-of-distribution (OOD) Detection: Masked Image Modeling is All You Need-
RP+GradNorm-79.80Detecting Out-of-distribution Data through In-distribution Class Prior
KNN (ResNet-50)97.1811.56Out-of-Distribution Detection with Deep Nearest Neighbors-
SHE-45.09Out-of-Distribution Detection based on In-Distribution Data Patterns Memorization with Modern Hopfield Energy
0 of 33 row(s) selected.