A curated list of awesome out-of-distribution detection resources.
- Training-driven OOD Detection
- Training-agnostic OOD Detection
- LPM-based OOD Detection
- Evaluation & Application
MOOD[Li et al.][CVPR 2023]Rethinking Out-of-distribution (OOD) Detection: Masked Image Modeling is All You Need[PDF][CODE]MOODv2[li et al.][arXiv]Moodv2: Masked image modeling for out-of-distribution detection.[PDF]PRE[osada et al.][WACV 2023]Out-of-Distribution Detection with Reconstruction Error and Typicality-based Penalty[PDF]- [graham et al.][CVPR 2023]Denoising diffusion models for out-of-distribution detection[PDF][CODE]
LMD[Liu et al.][ICML 2023]Unsupervised Out-of-Distribution Detection with Diffusion Inpainting[PDF][CODE]DiffGuard[Gao et al.][ICCV 2023]DiffGuard: Semantic Mismatch-Guided Out-of-Distribution Detection using Pre-trained Diffusion Models[PDF][CODE]DenoDiff[Graham et al.][CVPR 2023]Denoising diffusion models for out-of-distribution detection[PDF][CODE]MoodCat[Yang et al.][ECCV 2022]Out-of-distribution detection with semantic mismatch under masking[PDF][CODE]RAE[Yibo Zhou][CVPR 2022]Rethinking reconstruction autoencoder-based out-of-distribution detection[PDF]
LID[Kamkari et al.][ICML 2024] A Geometric Explanation of the Likelihood OOD Detection Paradox[PDF][CODE]HVCM[Li et al.][ICCV 2023]Hierarchical Visual Categories Modeling: A Joint Representation Learning and Density Estimation Framework for Out-of-Distribution Detection[PDF]DDR[Huang et al.][NeurIPS 2022]Density-driven Regularization for Out-of-distribution Detection[PDF]
UE-NL[Huang et al.][CAICE 2023]Uncertainty-estimation with normalized logits for out-of-distribution detection[PDF]DML[Zhang et al.][CVPR 2023]Decoupling MaxLogit for Out-of-Distribution Detection[PDF]LogitNorm[Wei et al.][ICML 2022]Mitigating neural network overconfidence with logit normalization[PDF][CODE]
SSOD[Sen Pei][ICLR 2024]Image background serves as good proxy for out-of-distribution data[PDF]SEM[Yang et al.][IJCV 2023]Full-Spectrum out-of-distribution detection[PDF][CODE]NPOS[Tao et al.][ICLR 2023]Non-parametric outlier synthesis[PDF][CODE]SHIFT[Kwon et al.][BMVC 2023]Improving Out-of-Distribution Detection Performance using Synthetic Outlier Exposure Generated by Visual Foundation Models[PDF][CODE]ATOL[Zheng et al.][NeurIPS 2023]Out-of-distribution Detection Learning with Unreliable Out-of-distribution Sources[PDF][CODE]CMG[Wang et al.][ECML 2022]CMG: A class-mixed generation approach to out-of-distribution detection[PDF][CODE]VOS[Du et al.][ICLR 2022]Vos: Learning what you don't know by virtual outlier synthesis[PDF][CODE]CODEs[Tang et al.][ICCV 2021]CODEs: Chamfer out-of-distribution examples against overconfidence issue[PDF]ConfiCali[Lee et al.][ICLR 2018]Training confidence-calibrated classifiers for detecting out-of-distribution samples[PDF][CODE]
PALM[Lu et al.][ICLR 2024]Learning with mixture of prototypes for out-of-distribution detection[PDF][CODE]ReweightOOD[Regmi et al.][CVPR 2024]Reweightood: Loss reweighting for distance-based ood detection[PDF]CIDER[Ming et al.][ICLR 2023]How to exploit hyperspherical embeddings for out-of-distribution detection?[PDF][CODE]Siren[Du et al.][NeurIPS 2022]Siren: Shaping representations for detecting out-of-distribution objects[PDF][CODE]Step[Zhou et al.][NeurIPS 2021]STEP : Out-of-Distribution Detection in the Presence of Limited In-distribution Labeled Data[PDF]
COOD[Hogeweg et al.][CVPR 2024]Cood: Combined out-of-distribution detection using multiple measures for anomaly & novel class detection in large-scale hierarchical classification[PDF]AREO[Sapkota et al.][ICLR 2023]Adaptive Robust Evidential Optimization For Open Set Detection from Imbalanced Data[PDF]IDCP[Jiang et al.][ICML 2023]Detecting out-of-distribution data through in-distribution class prior[PDF][CODE]Open-Sampling[Wei et al.][ICML 2023]Open-sampling: Exploring out-of-distribution data for re-balancing long-tailed datasets[PDF]II-Mixup[Mehta et al.][MICCAI 2022]Out-of-distribution detection for long-tailed and fine-grained skin lesion images[PDF][CODE]OLTR[Liu et al.][CVPR 2019]Large-scale long-tailed recognition in an open world[PDF][CODE]
MixOE[Zhang et al.][WACV 2023]Mixture Outlier Exposure: Towards Out-of-Distribution Detection in Fine-grained Environments[PDF][CODE]SSL-GOOD[Mohseni et al.][AAAI 2020]Self-supervised learning for generalizable out-of-distribution detection[PDF]EnergyOE[Liu et al.][NeurIPS 2020]Energy-based out-of-distribution detection[PDF][CODE]OE[Hendrycks et al.][ICLR 2019]Deep anomaly detection with outlier exposure[PDF][CODE]Why-RELU[Hein et al.][CVPR 2019]Why relu networks yield high-confidence predictions far away from the training data and how to mitigate the problem[PDF][CODE]ELOC[Vyas et al.][ECCV 2018]Out-of-distribution detection using an ensemble of self supervised leave-out classifier[PDF]
DAOL[Wang et al.][NeurIPS 2023]Learning to Augment Distributions for Out-of-Distribution Detection[PDF][CODE]DOE[Wang et al.][ICLR 2023]Out-of-distribution detection with implicit outlier transformation[PDF][CODE]MixOE[Zhang et al.][WACV 2023]Mixture Outlier Exposure: Towards Out-of-Distribution Detection in Fine-grained Environments[PDF][CODE]DivOE[Zhu et al.][NeurIPS 2023]Diversified Outlier Exposure for Out-of-Distribution Detection via Informative Extrapolation[PDF][CODE]POEM[Ming et al.][PMLR 2022]POEM: Out-of-Distribution Detection with Posterior Sampling[PDF][CODE]BD-Resamp[Li et al.][CVPR 2020]Background data resampling for outlier-aware classification[PDF][CODE]
COCL[Miao et al.][AAAI 2024]Out-of-Distribution Detection in Long-Tailed Recognition with Calibrated Outlier Class Learning[PDF][CODE]EAT[Wei et al.][AAAI 2024]EAT: Towards Long-Tailed Out-of-Distribution Detection[PDF][CODE]BERL[Choi et al.][CVPR 2023]Balanced Energy Regularization Loss for Out-of-distribution Detection[PDF]PASCAL[Wang et al.][ICML 2022]Partial and asymmetric contrastive learning for out-of-distribution detection in long-tailed recognition[PDF][CODE]
ZODE[Xue et al.][CVPR 2024]Enhancing the power of ood detection via sample-aware model selection[PDF]LogicOOD[Kirchheim et al.][WACV 2024]Out-of-distribution detection with logical reasoning[PDF][CODE]GEN[Liu et al.][CVPR 2023]GEN: Pushing the limits of softmax-based out-of-distribution detection[PDF][CODE]MaxLogits[Hendrycks et al.][ICML 2022]Scaling out-of-distribution detection for real-world setting[PDF][CODE]Energy[Liu et al.][NeurIPS 2020]Energy-based out-of-distribution detection[PDF][CODE]MSP[Hendrycks et al.][ICLR 2017]A baseline for detecting misclassified and out-of-distribution examples in neural networks[PDF][CODE]
NNGuide[Park et al.][ICCV 2023]Nearest neighbor guidance for out-of-distribution detection[PDF][CODE]KNN[Sun et al.][ICML 2022]Out-of-distribution detection with deep nearest neighbors[PDF][CODE]SSD[Sehwag et al.][ICLR 2021]Ssd: A unified framework for self-supervised outlier detection[PDF][CODE]Mahalanobis[Lee et al.][NeurIPS 2018]A simple unified framework for detecting out-of-distribution samples and adversarialattacks[PDF][CODE]
OPNP[Chen et al.][NeurIPS 2024]Optimal parameter and neuron pruning for out-of-distribution detection[PDF]GradOrth[Behpour et al.][NeurIPS 2023]GradOrth: A Simple yet Efficient Out-of-Distribution Detection with Orthogonal Projection of Gradients[PDF]GAIA[Chen et al.][NeurIPS 2023]GAIA: Delving into Gradient-based Attribution Abnormality for Out-of-distribution Detection[PDF]GradNorm[Huang et al.][NeurIPS 2021]On the importance of gradients for detecting distributional shifts in the wild[PDF][CODE]Grad[Lee et al.][ICIP 2020]Gradients as a measure of uncertainty in neural networks[PDF]
NAC[Liu et al.][ICLR 2024]Neuron activation coverage: Rethinking out-of-distribution detection and generalization[PDF][CODE]Neco[Ammar et al.][ICLR 2024]NECO: NEural Collapse Based Out-of-distribution detection[PDF][CODE]Optimal-FS[Zhao et al.][ICLR 2024]Towards optimal feature-shaping methods for out-of-distribution detection[PDF][CODE]BLOOD[Jelenić et al.][ICLR 2024]Out-of-distribution detection by leveraging between-layer transformation smoothness[PDF][CODE]SCALE[Xu et al.][ICLR 2024]Scaling for training time and post-hoc out-of-distribution detection enhancement[PDF][CODE]DDCS[Yuan et al.][CVPR 2024]Discriminability-driven channel selection for out-of-distribution detection[PDF]VRA[Xu et al.][NeurIPS 2023]VRA: Variational Rectified Activation for Out-of-distribution Detection[PDF][CODE]ASH[Djurisic et al.][ICLR 2023]Extremely simple activation shaping for out-of-distribution detection[PDF][CODE]LINe[Ahn et al.][CVPR 2023]LINe: Out-of-Distribution Detection by Leveraging Important Neurons[PDF][CODE]SHE[Zhang et al.][ICLR 2022]Out-of-distribution detection based on in-distribution data patterns memorization with modern hopfield energy[PDF][CODE]ViM[Wang et al.][CVPR 2022]Vim: Out-of-distribution with virtual-logit matching[PDF][CODE]ReAct[Sun et al.][NeurIPS 2021]ReAct: Out-of-distribution detection with rectified activations[PDF][CODE]ODIN[Liang et al.][ICLR 2018]Enhancing the reliability of out-of-distribution image detection in neural networks[PDF][CODE]
ConjNorm[Peng et al.][ICLR 2024]ConjNorm: Tractable Density Estimation for Out-of-Distribution Detection[PDF]GEM[Morteza et al.][AAAI 2022]Provable Guarantees for Understanding Out-of-distribution Detection[PDF][CODE]
-
...[Fang et al.][NeurIPS 2022]Is Out-of-Distribution Detection Learnable?[PDF] -
UniEnt[Gao et al.][arxiv 2024]Unified Entropy Optimization for Open-Set Test-Time Adaptation[PDF][CODE]
-
SAL[Du et al.][ICLR 2024]HOW DOES UNLABELED DATA PROVABLY HELP OUT-OF-DISTRIBUTION DETECTION? [PDF][CODE] -
ATTA[Gao et al.][NeurIPS 2023]ATTA: Anomaly-aware Test-Time Adaptation for Out-of-Distribution Detection in Segmentation[PDF][CODE] -
MOL[Wu et al.][CVPR 2023]Meta OOD Learning For Continuously Adaptive OOD Detection[PDF] -
SODA[Geng et al.][arxiv 2023]SODA: Stream Out-of-Distribution Adaptation[PDF] -
AUTO[Yang et al.][arxiv 2023]AUTO: Adaptive Outlier Optimization for Online Test-Time OOD Detection[PDF] -
WOODS[Katz-Samuels et al.][ICML 2022]Training OOD Detectors in their Natural Habitats[PDF][CODE]
-
RTL[Fan et al.][CVPR 2024]Test-time linear out-of-distribution detection[PDF][CODE] -
ETLT[Fan et al.][arxiv 2023/CVPR 2024]A Simple Test-Time Method for Out-of-Distribution Detection[PDF] -
GOODAT[Wang et al.][AAAI 2024]Towards Test-time Graph Out-of-Distribution Detection[PDF] -
AdaOOD[Zhang et al.][arxiv 2023]Model-free Test Time Adaptation for Out-Of-Distribution Detection[PDF]
-
One-Class-Anything[Ge et al.][arxiv 2023]Building One-class Detector for Anything: Open-vocabulary Zero-shot OOD Detection Using Text-image Models [PDF][CODE] -
...[Fort et al.][NeurIPS 2021]Exploring the Limits of Out-of-Distribution Detection[PDF][CODE]
RONIN[Nguyen et al.][arxiv 2024]Zero-Shot Object-Level Out-of-Distribution Detection with Context-Aware Inpainting[PDF]
-
SeTAR[Li et al.][NeurIPS 2024]SeTAR: Out-of-Distribution Detection with Selective Low-Rank Approximation[PDF][[https://github.com/X1AOX1A/SeTAR]] -
AdaNeg[Zhang et al.][NeurIPS 2024]AdaNeg: Adaptive Negative Proxy Guided OOD Detection with Vision-Language Models[PDF][CODE] -
CLIPScope[Fu et al.][arxiv 2024]CLIPScope: Enhancing Zero-Shot OOD Detection with Bayesian Scoring[PDF] -
LAPT[Zhang et al.][arxiv 2024]Label-driven Automated Prompt Tuning for OOD Detection with Vision-Language Model[PDF] -
NegLabel[Jiang et al.][ICLR 2024]Negative Label Guided OOD Detection with Pretrained Vision-Language Models[PDF][CODE] -
CLIPN[Wang et al.][ICCV 2022]CLIPN for Zero-Shot OOD Detection: Teaching CLIP to Say No[PDF][CODE] -
MCM[Ming et al.][NeurIPS 2022]Delving into Out-of-Distribution Detection with Vision-Language Representations [PDF][CODE] -
ZOC[S'Esmaeilpour et al.][AAAI 2022]Zero-Shot Out-of-Distribution Detection Based on the Pre-trained Model CLIP [PDF][CODE]
-
COOD[Liu et al.][arxiv 2024]COOD: Concept-based Zero-shot OOD Detection[PDF] -
CMA[Lee et al.][arxiv 2024]Reframing the Relationship in Out-of-Distribution Detection[PDF] -
ReGuide[Lee et al.][arxiv 2024]Reflexive Guidance: Improving OoDD in Vision-Language Models via Self-Guided Image-Adaptive Concept Generation[PDF] -
...[Salimben][arxiv 2024]Beyond fine-tuning: LoRA modules boost near-OOD detection and LLM security[PDF] -
VI-OOD[Zhan et al.][arxiv 2024]VI-OOD: A Unified Representation Learning Framework for Textual[PDF][CODE] -
...[Bendou et al.][arxiv 2024]LLM meets Vision-Language Models for Zero-Shot One-Class Classification[PDF][CODE] -
...[Liu et al.][arxiv 2024]How Good Are Large Language Models at Out-of-Distribution Detection?[PDF] -
...[Huang et al.][arxiv 2024]Out-of-Distribution Detection Using Peer-Class Generated by Large Language Model[PDF] -
...[Dai el al.][EMNLP 2023]Exploring Large Language Models for Multi-Modal Out-of-Distribution Detection[PDF]
OLE[Ding et al.][arxiv 2024]Zero-Shot Out-of-Distribution Detection with Outlier Label Exposure[PDF][CODE]
GL-MCM[Miyai et al.][arxiv 2023]Zero-Shot In-Distribution Detection in Multi-Object Settings Using Vision-Language Foundation Models[PDF][CODE]
...[Kim et al.][ICEIC 2024]Comparison of Out-of-Distribution Detection Performance of CLIP-based Fine-Tuning Methods[PDF]...[Ming et al.][IJCV 2023]How Does Fine-Tuning Impact Out-of-Distribution Detection for Vision-Language Models?[PDF]DSGF[Dong et al.][arxiv 2023]Towards Few-shot Out-of-Distribution Detection[PDF]...[Fort et al.][NeurIPS 2021]Exploring the Limits of Out-of-Distribution Detection[PDF][CODE]
-
HyperMix[Mehta et al.][WACV 2024]HyperMix: Out-of-Distribution Detection and Classification in Few-Shot Settings[PDF] -
OOD-MAML[Jeong et al.][NeurIPS 2020]OOD-MAML: Meta-Learning for Few-Shot Out-of-Distribution Detection and Classification[PDF][CODE]
-
ECS[Jung et al.][arxiv 2024]Enhancing Near OOD Detection in Prompt Learning: Maximum Gains, Minimal Costs[PDF] -
SCT[Yu et al.][NeurIPS 2024]Self-Calibrated Tuning of Vision-Language Models for Out-of-Distribution Detection[PDF][CODE] -
CLIP-OS[Sun et al.][arxiv 2024]CLIP-Driven Outliers Synthesis for Few-Shot Out-of-Distribution Detection[PDF] -
GalLop[Lafon et al.][arxiv 2024]GalLoP: Learning Global and Local Prompts for Vision-Language Model[PDF] -
TagOOD[Li et al.][arXiv 2024]Tagood: A novel approach to out-of-distribution detection via vision-language representations and class center learning[PDF] -
CRoFT[Zhu et al.][ICML 2024]Croft: Robust fine-tuning with concurrent optimization for ood generalization and open-set ood detection[PDF][CODE] -
EOK-Prompt[Zeng et al.][arxiv 2024]ENHANCING OUTLIER KNOWLEDGE FOR FEW-SHOT OUT-OF-DISTRIBUTION DETECTION WITH EXTENSIBLE LOCAL PROMPTS[PDF] -
NegPrompt[Li et al.][CVPR 2024]Learning Transferable Negative Prompts for Out-of-Distribution Detection[PDF][CODE] -
LSN[Nie et al.][ICLR 2024]Out-of-Distribution Detection with Negative Prompts[PDF][CODE] -
ID-like[Bai et al.][CVPR 2024]ID-like Prompt Learning for Few-Shot Out-of-Distribution Detection[PDF] -
LoCoOp[Miyai et al.][NeurIPS 2023]LoCoOp:Few-Shot Out-of-Distribution Detection via Prompt Learning[PDF][CODE] -
DSGF[Dong et al.][arxiv 2023]Towards Few-shot Out-of-Distribution Detection[PDF]
Dual-Adapter[Chen et al.][arxiv 2024]Dual-Adapter: Training-free Dual Adaptation for Few-shot Out-of-Distribution Detection[PDF]
-
NPOS[Tao et al.][ICLR 2023] NON-PARAMETRIC OUTLIER SYNTHESIS[PDF][CODE] -
TOE[Park et al.][NeurIPS 2023]On the Powerfulness of Textual Outlier Exposure for Visual OoD Detection[PDF][CODE] -
PT-OOD[Miyai et al.][arxiv 2023]CAN PRE-TRAINED NETWORKS DETECT FAMILIAR OUT-OF-DISTRIBUTION DATA?[PDF][CODE]
-
OpenOOD v1.5[Zhang et al.][NeurIPS 2023]OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detection[PDF][CODE] -
MOL[Wu et al.][CVPR 2023]Meta OOD Learning For Continuously Adaptive OOD Detection[PDF] -
NINCO[Bitterwolf et al.][ICML 2023]In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluation[PDF][CODE] -
OpenOOD[Yang et al.][NeruIPS 2022]OpenOOD: Benchmarking Generalized Out-of-Distribution Detection[PDF][CODE]
-
...[ Ancha et al.][ICRA 2024]Deep Evidential Uncertainty Estimation for Semantic Segmentation under OOD Obstacles[PDF][CODE] -
ATTA[Gao et al.][NeurIPS 2023]ATTA: Anomaly-aware Test-Time Adaptation for Out-of-Distribution Detection in Segmentation[PDF][CODE] -
...[Hendrycks et al.][ICML 2022]Scaling Out-of-Distribution Detection for Real-World Settings[PDF] -
SegmentMeIfYouCan[Chan et al.][NeurIPS 2021]SegmentMeIfYouCan: A Benchmark for Anomaly Segmentation[PDF] -
Fishyscapes Benchmark[Blum et al.][arxiv 2019]The Fishyscapes Benchmark: Measuring Blind Spots in Semantic Segmentation[PDF]
RONIN[Nguyen et al.][arxiv 2024]Zero-Shot Object-Level Out-of-Distribution Detection with Context-Aware Inpainting[PDF]SAFE[Wilson et al.][CVPR 2023]SAFE: Sensitivity-aware Features for Out-of-distribution Object Detection[PDF]SIREN[Du et al.][NuerIPS 2022]SIREN: Shaping Representations for Detecting Out-of-Distribution Objects[PDF][CODE]
...[Mao et al.][arxiv 2024]Language-Enhanced Latent Representations for Out-of-Distribution Detection in Autonomous Driving[PDF]
-
MultiOOD[Dong et al.][NeurIPS 2024]MultiOOD: Scaling Out-of-Distribution Detection for Multiple Modalities[PDF][CODE] -
...[Sim et al.][ECAI 2023]A Simple Debiasing Framework for Out-of-Distribution Detection in Human Action Recognition[PDF][CODE]
...[Giger et al.][Space Weather 2023]Unsupervised Anomaly Detection With Variational Autoencoders Applied to Full-Disk Solar Images [PDF]...[Dan et al.][ACM Trans. Cyber-Phys. Syst 2024]Interpretable Latent Space for Meteorological Out-of-Distribution Detection via Weak Supervision[PDF]
EndoOOD[Tan et al.][arxiv 2024]EndoOOD: Uncertainty-aware Out-of-distribution Detection in Capsule Endoscopy Diagnosis[PDF]...[Chen et al.][ICASSP 2024]Out-of-Distribution Detection for Learning-Based Chest X-Ray Diagnosis[PDF]
...[Xu et al.][arxiv 2024]Large Language Models for Anomaly and Out-of-Distribution Detection:A Survey[PDF]...[Lang et al.][TMLR 2023]A Survey on Out-of-Distribution Detection in NLP[PDF]
MILTOOD[Darrin et al.][AAAI 2024]Unsupervised Layer-Wise Score Aggregation for Textual OOD Detection[PDF]VI-OOD[Zhan et al.][arxiv 2024]VI-OOD: A Unified Representation Learning Framework for Textual Out-of-distribution Detection[PDF][CODE]Spatial-aware Adapter[Gu et al.][EMNLP 2023]A Critical Analysis of Document Out-of-Distribution Detection[PDF]Closer-look[Zhan et al.][Coling 2022]A Closer Look at Few-Shot Out-of-Distribution Intent Detection[PDF][CODE]DCL[Zhan et al.][ACL 2021]Out-of-scope intent detection with self-supervision and discriminative training [PDF][CODE]OOD-Text[Arora et al.][EMNLP 2021]Types of Out-of-Distribution Texts and How to Detect Them[PDF][CODE]
...[Bukhsh et al.][arxiv 2022]On Out-of-Distribution Detection for Audio with Deep Nearest Neighbors[PDF]...[Naranjo-Alcazar et al.][Sensors 2020]Open Set Audio Classification Using Autoencoders Trained on Few Data[PDF]...[Battaglino][IWAENC 2016]The Open-Set Problem in Acoustic Scene Classification[PDF]
...[Ju et al.][arxiv 2024]A Survey of Graph Neural Networks in Real world: Imbalance, Noise, Privacy and OOD Challenges[PDF]
GOODAT[Wang et al.][AAAI 2024]Towards Test-time Graph Out-of-Distribution Detection[PDF]GOOD-D[Liu et al.][WSDM 2023]GOOD-D: On Unsupervised Graph Out-Of-Distribution Detection[PDF][CODE]
DEXTER[Nasvytis et al.]/[arxiv 2024]Rethinking Out-of-Distribution Detection for Reinforcement[PDF] Learning: Advancing Methods for Evaluation and DetectionAlberDICE[Matsunaga et al.][NuerIPS 2023]AlberDICE: Addressing Out-Of-Distribution Joint Actions in Offline Multi-Agent RL via Alternating Stationary Distribution Correction Estimation[PDF]