SOTAVerified

Out-of-Distribution Detection

Detect out-of-distribution or anomalous examples.

Papers

Showing 401–450 of 888 papers

TitleStatusHype
Non-Generative Energy Based Models—0
Establishing baselines and introducing TernaryMixOE for fine-grained out-of-distribution detection—0
Nearest Neighbor Based Out-of-Distribution Detection in Remote Sensing Scene Classification—0
Diffusion Denoised Smoothing for Certified and Adversarial Robust Out-Of-Distribution DetectionCode0
SIO: Synthetic In-Distribution Data Benefits Out-of-Distribution DetectionCode0
LINe: Out-of-Distribution Detection by Leveraging Important NeuronsCode1
Calibrated Out-of-Distribution Detection with a Generic RepresentationCode0
A Global Model Approach to Robust Few-Shot SAR Automatic Target Recognition—0
Uncertainty-Aware Optimal Transport for Semantically Coherent Out-of-Distribution DetectionCode1
Improving Out-of-Distribution Detection with Disentangled Foreground and Background FeaturesCode0
WDiscOOD: Out-of-Distribution Detection via Whitened Linear Discriminant AnalysisCode0
InPL: Pseudo-labeling the Inliers First for Imbalanced Semi-supervised Learning—0
MCROOD: Multi-Class Radar Out-Of-Distribution Detection—0
Adapting Contrastive Language-Image Pretrained (CLIP) Models for Out-of-Distribution DetectionCode0
Out-of-distribution Detection with Implicit Outlier TransformationCode1
Predicted Embedding Power Regression for Large-Scale Out-of-Distribution Detection—0
Non-Parametric Outlier SynthesisCode1
How to Construct Energy for Images? Denoising Autoencoder Can Be Energy Based Model—0
Rule-based Out-Of-Distribution DetectionCode0
Average of Pruning: Improving Performance and Stability of Out-of-Distribution Detection—0
Reconstruction-based Out-of-Distribution Detection for Short-Range FMCW Radar—0
What Can We Learn From The Selective Prediction And Uncertainty Estimation Performance Of 523 Imagenet ClassifiersCode1
A framework for benchmarking class-out-of-distribution detection and its application to ImageNetCode1
VRA: Variational Rectified Activation for Out-of-distribution Detection—0
Steerable Equivariant Representation Learning—0
Variational Boosted Soft Trees—0
MalProtect: Stateful Defense Against Adversarial Query Attacks in ML-based Malware Detection—0
Unsupervised Out-of-Distribution Detection with Diffusion InpaintingCode1
Unsupervised Evaluation of Out-of-distribution Detection: A Data-centric Perspective—0
Uncertainty-Estimation with Normalized Logits for Out-of-Distribution Detection—0
Robustness to Spurious Correlations Improves Semantic Out-of-Distribution Detection—0
How Reliable is Your Regression Model's Uncertainty Under Real-World Distribution Shifts?Code1
Trust, but Verify: Using Self-Supervised Probing to Improve TrustworthinessCode0
Energy-based Out-of-Distribution Detection for Graph Neural NetworksCode1
Cluster-aware Contrastive Learning for Unsupervised Out-of-distribution Detection—0
Rethinking Out-of-distribution (OOD) Detection: Masked Image Modeling is All You NeedCode1
AIROGS: Artificial Intelligence for RObust Glaucoma Screening ChallengeCode0
Turning the Curse of Heterogeneity in Federated Learning into a Blessing for Out-of-Distribution DetectionCode1
Fine-Tuning Deteriorates General Textual Out-of-Distribution Detection by Distorting Task-Agnostic FeaturesCode1
Plugin estimators for selective classification with out-of-distribution detection—0
Master's Thesis: Out-of-distribution Detection with Energy-based ModelsCode0
A Data-Centric Approach for Improving Adversarial Training Through the Lens of Out-of-Distribution Detection—0
Interpretable Out-Of-Distribution Detection Using Pattern Identification—0
Out-of-Distribution Detection based on In-Distribution Data Patterns Memorization with Modern Hopfield EnergyCode0
A Multi-Scale Framework for Out-of-Distribution Detection in Dermoscopic Images—0
Simple and Effective Out-of-Distribution Detection via Cosine-based Softmax Loss—0
Revisit PCA-based Technique for Out-of-Distribution DetectionCode0
Probabilistic Knowledge Distillation of Face Ensembles—0
GEN: Pushing the Limits of Softmax-Based Out-of-Distribution DetectionCode1
Decoupling MaxLogit for Out-of-Distribution Detection—0
Show:102550
← PrevPage 9 of 18Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViM (BiT)AUROC98.92—Unverified
2NAC-UE (ResNet-50)AUROC97.9—Unverified
3ASH-S (ResNet-50)AUROC97.6—Unverified
4SCALE (ResNet50)AUROC97.37—Unverified
5KNN (ResNet-50)AUROC97.18—Unverified
6DisCoPatchAUROC96.4—Unverified
7NNGuide (ResNet50 w/ ReAct)AUROC96.11—Unverified
8NNGuide (RegNet)AUROC95.82—Unverified
9ViM (ViT-B/16)AUROC95.34—Unverified
10KNN (ResNet-50 SupCon)AUROC94.45—Unverified
#ModelMetricClaimedVerifiedStatus
1CMA(ViT-B/16, NegLabel)AUROC99.62—Unverified
2NNGuide (RegNet)AUROC99.57—Unverified
3ViM (ViT-B/16)AUROC99.41—Unverified
4DisCoPatchAUROC99.1—Unverified
5SCALE (ResNet50)AUROC98.17—Unverified
6MOS (BiT-S-R101x1)AUROC98.15—Unverified
7ASH-S (ResNet-50)AUROC97.87—Unverified
8NNGuide (ResNet50 w/ ReAct)AUROC97.7—Unverified
9BATS (ResNet-50)AUROC97.67—Unverified
10LINe (ResNet-50)AUROC97.56—Unverified
#ModelMetricClaimedVerifiedStatus
1MOODAUROC88.5—Unverified
2RP+GradNormFPR9583.29—Unverified
3KNN (ResNet-50)FPR9577.09—Unverified
4Watermarking (WRN-40-2 w/ Energy)FPR9571.85—Unverified
5Watermarking (WRN-40-2 w/ MSP)FPR9570.59—Unverified
6DOEFPR9567.84—Unverified
7DMLFPR9561.43—Unverified
8GradNorm (ResNetv2-101)FPR9560.86—Unverified
9KNN (ResNet-50 SupCon)FPR9560.02—Unverified
10ReAct (ResNet-50)FPR9551.56—Unverified
#ModelMetricClaimedVerifiedStatus
1MOODAUROC89.8—Unverified
2DOEFPR9580.94—Unverified
3RP+GradNormFPR9573.53—Unverified
4KNN (ResNet-50)FPR9569.53—Unverified
5DMLFPR9557.4—Unverified
6SHEFPR9554.19—Unverified
7ODIN+UMAP (ResNet-50)FPR9549.69—Unverified
8KNN (ResNet-50 SupCon)FPR9548.91—Unverified
9ReAct (ResNet-50)FPR9547.69—Unverified
10GradNorm (ResNetv2-101)FPR9546.48—Unverified
#ModelMetricClaimedVerifiedStatus
1MOODAUROC89.1—Unverified
2RP+GradNormFPR9570.12—Unverified
3DOEFPR9559.83—Unverified
4DMLFPR9554.74—Unverified
5ODIN+UMAP (ResNet-50)FPR9540.94—Unverified
6MOS (BiT-S-R101x1)FPR9539.97—Unverified
7MCM (CLIP-L)FPR9538.17—Unverified
8NPOSFPR9537.93—Unverified
9RankFeat (ResNetv2-101)FPR9536.8—Unverified
10DICE + ReAct (ResNet-50)FPR9527.25—Unverified
#ModelMetricClaimedVerifiedStatus
1DHMAUROC100—Unverified
2Ensemble of ViTsAUROC98.11—Unverified
3ViT-L_16 finetuned on CIFAR-100AUROC97.98—Unverified
4R50+ViT_B-16 finetuned on CIFAR-100AUROC96.23—Unverified
5ViT_B-16 finetuned on CIFAR-100AUROC95.53—Unverified
6MLP-Mixer_B-16 finetuned on CIFAR-100AUROC95.31—Unverified
7CLIP using class name words describing the two distributionsAUROC94.68—Unverified
8ERD (ResNet18)AUROC94.3—Unverified
9OpenHybridAUROC85.6—Unverified
10Maximum Logit Score (MLS)AUROC83.2—Unverified
#ModelMetricClaimedVerifiedStatus
1DHMAUROC100—Unverified
2R+ViT finetuned on CIFAR-10AUROC98.52—Unverified
3ViT finetuned on CIFAR-10AUROC98.42—Unverified
4MLP-Mixer finetuned on CIFAR-10AUROC97.85—Unverified
5ZODE-KNNAUROC97.12—Unverified
6OpenHybridAUROC95.1—Unverified
7ERD (ResNet18)AUROC95.1—Unverified
8Wide 40-2 + OECCAUROC94.9—Unverified
9WRN 40-2 + OEAUROC93.3—Unverified
10Isolation Forest on EfficientNet Softmax valuesAUROC91.95—Unverified
#ModelMetricClaimedVerifiedStatus
1DHMAUROC100—Unverified
2Wide ResNet 40x2AUROC99.9—Unverified
3ResNet 34 + OECC+GMAUROC99.7—Unverified
4ResNet 34 + FSSDAUROC99.5—Unverified
5Wide ResNet 40x2AUROC99.43—Unverified
6ZODE-KNNAUROC99.12—Unverified
7ResNet18 + APR-PAUROC98.1—Unverified
8WRN 40-2 + OEAUROC97.8—Unverified
9WRN 40-2 (MSP Baseline)AUROC97.8—Unverified
10WRN 40-2 + Rotation PredictionAUROC96.2—Unverified
#ModelMetricClaimedVerifiedStatus
1NNGuide (RegNet)AUROC97.73—Unverified
2ViM (ViT-B/16)AUROC97.61—Unverified
3DisCoPatchAUROC94.4—Unverified
4NNGuide (ResNet50 w/ ReAct)AUROC92.49—Unverified
5NAC-UE (ResNet-50)AUROC91.45—Unverified
6GENAUROC80.43—Unverified
#ModelMetricClaimedVerifiedStatus
1Mixup (Gaussian)Percentage correct95.93—Unverified
2Mixup (Imagenet)Percentage correct83.28—Unverified
3Baseline (Imagenet)Percentage correct80.57—Unverified
4Dropout(Imagenet)Percentage correct78.93—Unverified
5Baseline (Gaussian)Percentage correct73.28—Unverified
6Dropout(Gaussian)Percentage correct70.57—Unverified
#ModelMetricClaimedVerifiedStatus
1OECC + MDAUROC98.7—Unverified
2DenseNet-BC-100AUROC98.4—Unverified
3ResNet-34AUROC97.9—Unverified
4CSNNAUROC87.2—Unverified
5OEAUROC86.9—Unverified
#ModelMetricClaimedVerifiedStatus
1RbAAP66.82—Unverified
2DOoDAP63.03—Unverified
3cDNPAP62.35—Unverified
4GMMSegAP47.6—Unverified
#ModelMetricClaimedVerifiedStatus
1WRN 40-2 (MSP Baseline)FPR9562.66—Unverified
2WRN 40-2 + OEFPR9538.5—Unverified
3WRN 40-2 + OECCFPR9528.89—Unverified
4Wide ResNet 40x2FPR9523.4—Unverified
#ModelMetricClaimedVerifiedStatus
1ViT-B-384 Mahalanobis (pre-trained on IN-21k)AUROC95—Unverified
2DisCoPatchAUROC94.3—Unverified
3EffNetv2-M Relative MahalanobisAUROC88.9—Unverified
4EffNetb7 Relative Cosine SimAUROC87.9—Unverified
#ModelMetricClaimedVerifiedStatus
1ResNeXt50 + FSSDAUROC86.7—Unverified
2ResNeXt 50 + Maha distanceAUROC82.5—Unverified
3ResNeXt 50 + ODINAUROC61.3—Unverified
4ResNeXt 50 + OEAUROC52.6—Unverified
#ModelMetricClaimedVerifiedStatus
1GENFPR9597.3—Unverified
2ViM (ViT-B/16)FPR9536.75—Unverified
3NNGuide-ViM (ViT-B/16)FPR9533.1—Unverified
#ModelMetricClaimedVerifiedStatus
1ResNet34 + FSSDAUROC93.1—Unverified
2ResNet 34 + OEAUROC92.5—Unverified
3ResNet 34 + ODINAUROC90.8—Unverified
#ModelMetricClaimedVerifiedStatus
12-Layered GRUAUROC99.6—Unverified