-
A Comprehensive Review of Trends, Applications and Challenges In Out-of-Distribution Detection (Arxiv 2022) [Paper]
-
Out-Of-Distribution Generalization on Graphs: A Survey (Arxiv 2022) [Paper]
-
A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challenges (TMLR 2023) [Paper]
-
Generalized Out-of-Distribution Detection: A Survey (Arxiv 2021) [Paper]
-
Towards Out-Of-Distribution Generalization: A Survey (Arxiv 2021) [Paper]
-
A Survey on Assessing the Generalization Envelope of Deep Neural Networks: Predictive Uncertainty, Out-of-distribution and Adversarial Samples (Arxiv 2020) [Paper]
-
Mind the Label Shift of Augmentation-based Graph OOD Generalization (CVPR 2023) [Paper]
-
Balanced Energy Regularization Loss for Out-of-distribution Detection (CVPR 2023) [Paper]
-
NICO++: Towards better bechmarks for Out-of-Distribution Generalization (CVPR 2023) [Paper]
-
LINe: Out-of-Distribution Detection by Leveraging Important Neurons (CVPR 2023) [Paper]
-
Detection of out-of-distribution samples using binary neuron activation patterns (CVPR 2023) [Paper]
-
Decoupling MaxLogit for Out-of-Distribution Detection (CVPR 2023) [Paper]
-
Rethinking Out-of-Distribution Detection: Masked Image Modeling is All You Need (CVPR 2023) [Paper]
-
Out-of-Distributed Semantic Pruning for Robust Semi-Supervised Learning (CVPR 2023) [Paper]
-
Devil is in the Queries: Advancing Mask Transformers for Real-world Medical Image Segmentation and Out-of-Distribution Localization (CVPR 2023) [Paper]
-
GEN: Pushing the Limits of Softmax-Based Out-of-Distribution Detection (CVPR 2023) [Paper]
-
Are Data-driven Explanations Robust against Out-of-distribution Data? (CVPR 2023) [Paper]
-
Uncertainty-Aware Optimal Transport for Semantically Coherent Out-of-Distribution Detection (CVPR 2023) [Paper]
-
Distribution Shift Inversion for Out-of-Distribution Prediction (CVPR 2023) [Paper]
-
PoseExaminer: Automated Testing of Out-of-Distribution Robustness in Human Pose and Shape Estimation (CVPR 2023) [Paper]
-
Block Selection Method for Using Feature Norm in Out-of-Distribution Detection (CVPR 2023) [Paper]
-
Offline RL with No OOD Actions: In-Sample Learning via Implicit Value Regularization (ICLR 2023 top 5%) [Paper]
-
Harnessing Out-Of-Distribution Examples via Augmenting Content and Style (ICLR 2023) [Paper]
Datasets: SVHN, CIFAR10, LSUN, DTD, CUB, Flowers, Caltech, Dogs -
Out-of-Distribution Detection and Selective Generation for Conditional Language Models (ICLR 2023 top 25%) [Paper]
-
A framework for benchmarking Class-out-of-distribution detection and its application to ImageNet (ICLR 2023 top 25%) [Paper]
-
Turning the Curse of Heterogeneity in Federated Learning into a Blessing for Out-of-Distribution Detection (ICLR 2023 top 25%) [Paper]
-
Modeling the Data-Generating Process is Necessary for Out-of-Distribution Generalization (ICLR 2023 top 25%) [Paper]
-
Extremely Simple Activation Shaping for Out-of-Distribution Detection (ICLR 2023) [Paper]
-
The Tilted Variational Autoencoder: Improving Out-of-Distribution Detection (ICLR 2023) [Paper]
-
Pareto Invariant Risk Minimization: Towards Mitigating the Optimization Dilemma in Out-of-Distribution Generalization (ICLR 2023) [Paper]
-
Out-of-Distribution Detection based on In-Distribution Data Patterns Memorization with Modern Hopfield Energy (ICLR 2023) [Paper]
-
Improving Out-of-distribution Generalization with Indirection Representations (ICLR 2023) [Paper]
-
Out-of-distribution Detection with Implicit Outlier Transformation (ICLR 2023) [Paper]
-
Topology-aware Robust Optimization for Out-of-Distribution Generalization (ICLR 2023) [Paper]
-
Out-of-distribution Representation Learning for Time Series Classification (ICLR 2023) [Paper]
-
How to Exploit Hyperspherical Embeddings for Out-of-Distribution Detection? (ICLR 2023) [Paper]
-
Energy-based Out-of-Distribution Detection for Graph Neural Networks (ICLR 2023) [Paper]
-
Don’t forget the nullspace! Nullspace occupancy as a mechanism for out of distribution failure (ICLR 2023) [Paper]
-
InPL: Pseudo-labeling the Inliers First for Imbalanced Semi-supervised Learning (ICLR 2023) [Paper]
-
Diversify and Disambiguate: Out-of-Distribution Robustness via Disagreement (ICLR 2023) [Paper]
-
On the Effectiveness of Out-of-Distribution Data in Self-Supervised Long-Tail Learning. (ICLR 2023) [Paper]
-
Can Agents Run Relay Race with Strangers? Generalization of RL to Out-of-Distribution Trajectories (ICLR 2023) [Paper]
-
Mixture Outlier Exposure: Towards Out-of-Distribution Detection in Fine-Grained Environments (WACV 2023) [Paper] [Code]
Datasets: WebVision 1.0
Task: Out-of-Distribution Detection Images -
Out-of-Distribution Detection via Frequency-Regularized Generative Models (WACV 2023) [Paper] [Code]
Datasets: CIFAR-10, Fashion-MNIST (ID), SVHN, LSUN, MNIST, KMNIST, Omniglot, NotMNIST, Noise, Constant
Task: Out-of-Distribution Detection Images -
Hyperdimensional Feature Fusion for Out-of-Distribution Detection (WACV 2023) [Paper] [Code]
Datasets: CIFAR10 and CIFAR100 (ID), iSUN, TinyImageNet (croppedand resized: TINc and TINr), LSUN (cropped and resized: LSUNc and LSUNr), SVHN, MNIST, KMNIST, FashionMNIST, Textures
Task: Out-of-Distribution Detection Images -
Out-of-Distribution Detection With Reconstruction Error and Typicality-Based Penalty (WACV 2023) [Paper]
Datasets: CIFAR-10, TinyImageNet, and ILSVRC2012
Task: Out-of-Distribution Detection Image Reconstruction -
Heatmap-Based Out-of-Distribution Detection (WACV 2023) [Paper] [Code]
Datasets: CIFAR-10, CIFAR-100 and Tiny ImageNet
Task: Out-of-Distribution Detection Images
- VRA: Out-of-Distribution Detection with variational rectified activations (Arxiv 2023) [Paper]
-
OoD-Bench: Quantifying and Understanding Two Dimensions of Out-of-Distribution Generalization (CVPR 2022) [Paper] [Code]
Datasets: PACS; Office Home; TerraInc; Camelyon17; Colored MNIST; NICO; CelebA
Task: Image Classification -
Evading the Simplicity Bias: Training a Diverse Set of Models Discovers Solutions With Superior OOD Generalization (CVPR 2022) [Paper] [Code]
Datasets: [MNIST;CIFAR; Fashion-MNIST; SVHN] Biased activity recognition (BAR); PACS
Task: Image Classification -
Weakly Supervised Semantic Segmentation Using Out-of-Distribution Data (CVPR 2022) [Paper] [Code]
Datasets: Pascal VOC 2012, OpenImages, hard OoD dataset
Task: Semantic Segmentation -
DeepFace-EMD: Re-Ranking Using Patch-Wise Earth Mover's Distance Improves Out-of-Distribution Face Identification (CVPR 2022) [Paper] [Code]
Datasets: LFW, LFW-crop
Task: Face Identification -
Neural Mean Discrepancy for Efficient Out-of-Distribution Detection (CVPR 2022) [Paper]
Datasets: CIFAR-10, CIFAR-100, SVHN, croppedImageNet, cropped LSUN, iSUN, and Texture
Task: Image Classification -
Deep Hybrid Models for Out-of-Distribution Detection (CVPR 2022) [Paper]
Datasets: CIFAR-10 and CIFAR-100, SVHN, CLINC150
Task: Image Classification -
Amodal Segmentation Through Out-of-Task and Out-of-Distribution Generalization With a Bayesian Model (CVPR 2022) [Paper] [Code]
Datasets: OccludedVehicles; KINS; COCOA-cls
Task: Instance Segmentation -
Rethinking Reconstruction Autoencoder-Based Out-of-Distribution Detection (CVPR 2022) [Paper]
Datasets: CIFAR10; CIFAR100
Task: Image Classification -
ViM: Out-of-Distribution With Virtual-Logit Matching (CVPR 2022) [Paper] [Code]
Datasets: OpenImage-O; Texture; iNaturalist, ImageNet-O
Task: Image Classification -
Out-of-Distribution Generalization With Causal Invariant Transformations (CVPR 2022) [Paper] [Code]
Datasets: PACS; VLCS {VOC2007, LabelMe, Caltech101, SUN09}
Task: Image Classification -
Trustworthy Long-Tailed Classification (CVPR 2022) [Paper]
Datasets: (CIFAR-10-LT, CIFAR-100-LT and ImageNet-LT) and three balanced OOD datasets (SVHN, ImageNet-open and Places-open)
Task: Image Classification
-
Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution (ICLR 2022 Oral) [Paper] [Code]
Datasets: DomainNet, BREEDS-Living-17, BREEDS-Entity-30, CIFAR-10→STL, CIFAR-10→CIFAR-10.1, ImageNet-1K — where the OODtest sets are ImageNetV2, ImageNet-R, ImageNet-A, and ImageNet-Sketch —, FMoW Geo-shift -
Vision-Based Manipulators Need to Also See from Their Hands (ICLR 2022 Oral) [Paper] [Code]
Datasets: PyBullet physics engine, Meta-World -
Asymmetry Learning for Counterfactually-invariant Classification in OOD Tasks (ICLR 2022 Oral) [Paper]
Datasets: MNIST-{3,4},... -
Poisoning and Backdooring Contrastive Learning (ICLR 2022 Oral) [Paper]
Datasets: Conceptual Captions dataset -
Representational Continuity for Unsupervised Continual Learning (ICLR 2022 Oral) [Paper] [Code]
Datasets: Split CIFAR-10, Split CIFAR-100, Split Tiny-ImageNet -
Natural Posterior Network: Deep Bayesian Predictive Uncertainty for Exponential Family Distributions (ICLR 2022 Spotlight) [Paper]
Datasets: Sensorless Drive, MNIST, FMNIST, CIFAR-10 -
Pessimistic Bootstrapping for Uncertainty-Driven Offline Reinforcement Learning (ICLR 2022 Spotlight) [Paper] [Code]
Datasets: Gym -
Compositional Attention: Disentangling Search and Retrieval (ICLR Spotlight 2022) [Paper] [Code]
Datasets: Sort-of-CLEVR, CIFAR10, FashionMNIST, SVHN, Equilateral Triangle Detection -
Asymmetry Learning for Counterfactually-invariant Classification in OOD Tasks? (ICLR 2022 Oral) [Paper]
-
Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution (ICLR 2022 Oral) [Paper]
-
Vision-Based Manipulators Need to Also See from Their Hands (ICLR 2022 Oral) [Paper]
-
Uncertainty Modeling for Out-of-Distribution Generalization (ICLR 2022) [Paper]
-
Igeood: An Information Geometry Approach to Out-of-Distribution Detection (ICLR 2022) [Paper]
-
Revisiting flow generative models for Out-of-distribution detection (ICLR 2022) [Paper]
-
Invariant Causal Representation Learning for Out-of-Distribution Generalization (ICLR 2022) [Paper]
-
PI3NN: Out-of-distribution-aware Prediction Intervals from Three Neural Networks (ICLR 2022) [Paper]
-
A Statistical Framework for Efficient Out of Distribution Detection in Deep Neural Networks (ICLR 2022) [Paper]
-
Leveraging unlabeled data to predict out-of-distribution performance (ICLR 2022) [Paper]
-
Out-of-distribution Generalization in the Presence of Nuisance-Induced Spurious Correlations (ICLR 2022) [Paper]
-
The Role of Pretrained Representations for the OOD Generalization of RL Agents (ICLR 2022) [Paper]
-
Is Out-of-Distribution Detection Learnable? (NeurIPS 2022 Outstanding) [Paper]
-
Towards Out-of-Distribution Sequential Event Prediction: A Causal Treatment (NeurIPS 2022) [Paper]
-
GraphDE: A Generative Framework for Debiased Learning and Out-of-Distribution Detection on Graphs (NeurIPS 2022) [Paper]
-
Provably Adversarially Robust Detection of Out-of-Distribution Data (Almost) for Free (NeurIPS 2022) [Paper]
-
Your Out-of-Distribution Detection Method is Not Robust! (NeurIPS 2022) [Paper]
-
Density-driven Regularization for Out-of-distribution Detection (NeurIPS 2022) [Paper]
-
GOOD: A Graph Out-of-Distribution Benchmark (NeurIPS 2022) [Paper]
-
Learning Substructure Invariance for Out-of-Distribution Molecular Representations (NeurIPS 2022) [Paper]
-
Assaying Out-Of-Distribution Generalization in Transfer Learning (NeurIPS 2022) [Paper]
-
Functional Indirection Neural Estimator for Better Out-of-distribution Generalization (NeurIPS 2022) [Paper]
-
ZooD: Exploiting Model Zoo for Out-of-Distribution Generalization (NeurIPS 2022) [Paper]
-
Multi-Instance Causal Representation Learning for Instance Label Prediction and Out-of-Distribution Generalization (NeurIPS 2022) [Paper]
-
RankFeat: Rank-1 Feature Removal for Out-of-distribution Detection (NeurIPS 2022) [Paper]
-
Delving into Out-of-Distribution Detection with Vision-Language Representations (NeurIPS 2022) [Paper]
-
Learning Invariant Graph Representations for Out-of-Distribution Generalization (NeurIPS 2022) [Paper]
-
OpenOOD: Benchmarking Generalized Out-of-Distribution Detection (NeurIPS 2022) [Paper]
-
Out-of-Distribution Detection with An Adaptive Likelihood Ratio on Informative Hierarchical VAE (NeurIPS 2022) [Paper]
-
Boosting Out-of-distribution Detection with Typical Features (NeurIPS 2022) [Paper]
-
Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphs (NeurIPS 2022) [Paper]
-
Evaluating Out-of-Distribution Performance on Document Image Classifiers (NeurIPS 2022) [Paper]
-
Improving Out-of-Distribution Generalization by Adversarial Training with Structured Priors (NeurIPS 2022) [Paper]
-
Diverse Weight Averaging for Out-of-Distribution Generalization (NeurIPS 2022) [Paper]
-
Using Mixup as a Regularizer Can Surprisingly Improve Accuracy & Out-of-Distribution Robustness (NeurIPS 2022) [Paper]
-
Watermarking for Out-of-distribution Detection (NeurIPS 2022) [Paper]
-
SIREN: Shaping Representations for Detecting Out-of-Distribution Objects (NeurIPS 2022) [Paper]
-
Out-of-Distribution Detection via Conditional Kernel Independence Model (NeurIPS 2022) [Paper]
-
Open-Sampling: Exploring Out-of-Distribution Data for Re-balancing long-tailed Datasets (ICML 2022) [Paper] [Code]
Datasets: long-tailed CIFAR10/100, CelebA-5, Places-LT
Task: Image Classification -
Partial and Asymmetric Contrastive Learning for Out-of-Distribution Detection in Long-Tailed Recognition (ICML 2022) [Paper] [Code]
Datasets: CIFAR10-LT, CIFAR100-LT, and ImageNet-LT
Task: Image Classification -
Training OOD Detectors in their Natural Habitats (ICML 2022) [Paper] [Code]
Datasets: CIFAR10, CIFAR100 (ID), SVHN, Textures, Places365, LSUN-Crop, LSUN-Resize
Task: Image Classification -
Model Agnostic Sample Reweighting for Out-of-Distribution Learning (ICML 2022) [Paper]
-
Predicting Out-of-Distribution Error with the Projection Norm (ICML 2022) [Paper]
-
Fishr: Invariant Gradient Variances for Out-of-Distribution Generalization (ICML 2022) [Paper]
-
POEM: Out-of-Distribution Detection with Posterior Sampling (ICML 2022) [Paper]
-
Improved StyleGAN-v2 based Inversion for Out-of-Distribution Images (ICML 2022) [Paper]
-
Scaling Out-of-Distribution Detection for Real-World Settings (ICML 2022) [Paper]
-
Breaking Down Out-of-Distribution Detection: Many Methods Based on OOD Training Data Estimate a Combination of the Same Core Quantities (ICML 2022) [Paper]
-
Improving Out-of-Distribution Robustness via Selective Augmentation (ICML 2022) [Paper]
-
Out-of-Distribution Detection with Deep Nearest Neighbors (ICML 2022) [Paper]
-
OOD-CV: A Benchmark for Robustness to Out-of-Distribution Shifts of Individual Nuisances in Natural Images (ECCV 2022) [Paper]
Datasets: PASCAL3D+; OOD-CV
Task: Image Classification, Object Detection, and 3D Pose Estimation -
Out-of-Distribution Identification: Let Detector Tell Which I Am Not Sure (ECCV 2022) [Paper]
Datasets: PASCAL VOC-IO; Crack Defect
Task: Image Classification -
Out-of-Distribution Detection with Boundary Aware Learning (ECCV 2022) [Paper]
Datasets: CIFAR-10 and CIFAR-100; SVHN and LSUN; TinyImageNet; MNIST; Fashion-MNIST; Omniglot
Task: Image Classification -
Out-of-Distribution Detection with Semantic Mismatch under Masking (ECCV 2022) [Paper] [Code]
Datasets: Cifar-10, Cifar-100, SVHN, Texture, Places365, Lsun and Tiny-ImageNet
Task: Image Classification -
DICE: Leveraging Sparsification for Out-of-Distribution Detection (ECCV 2022) [Paper] [Code]
Datasets: CIFAR10; CIFAR100; Places365; Textures; iNaturalist; and SUN
Task: Image Classification -
Class Is Invariant to Context and Vice Versa: On Learning Invariance for Out-of-Distribution Generalization (ECCV 2022) [Paper] [Code]
Datasets: Colored MNIST; Corrupted CIFAR-10, Biased Action Recognition(BAR); PACS
Task: Image Classification -
Data Invariants to Understand Unsupervised Out-of-Distribution Detection (ECCV 2022) [Paper]
Datasets: CIFAR10; MVTec; SVHN; CIFAR100; DomainNet; coherence tomography (OCT); chest X-ray
Task: Image Classification -
Embedding Contrastive Unsupervised Features to Cluster in- and Out-of-Distribution Noise in Corrupted Image Datasets (ECCV 2022) [Paper] [Code]
Datasets: (mini) Webvision
Task: Image Classification
-
Gradient-Based Novelty Detection Boosted by Self-Supervised Binary Classification (AAAI 2022) [Paper]
Datasets: CIFAR-10, CIFAR-100, SVHN and TinyImageNet
Task: Image Classification -
Provable Guarantees for Understanding Out-of-distribution Detection (AAAI 2022) [Paper]
-
On the Impact of Spurious Correlation for Out-of-Distribution Detection (AAAI 2022) [Paper]
-
OoDHDR-Codec: Out-of-Distribution Generalization for HDR Image Compression (AAAI 2022) [Paper]
-
Zero-Shot Out-of-Distribution Detection Based on the Pre-Trained Model CLIP (AAAI 2022) [Paper]
-
iDECODe: In-Distribution Equivariance for Conformal Out-of-Distribution Detection (AAAI 2022) [Paper]
-
Exploiting Mixed Unlabeled Data for Detecting Samples of Seen and Unseen Out-of-Distribution Classes (AAAI 2022) [Paper]
-
VITA: A Multi-Source Vicinal Transfer Augmentation Method for Out-of-Distribution Generalization (AAAI 2022) [Paper]
-
Learning Modular Structures That Generalize Out-of-Distribution (Student Abstract) (AAAI 2022) [Paper]
-
Out-of-Distribution Detection in Unsupervised Continual Learning (CVPRw 2022) [Paper]
Datasets: CIFAR-100
Task: Image Classification -
Continual Learning Based on OOD Detection and Task Masking (CVPRw 2022) [Paper] [Code]
Datasets: MNIST-5T; CIFAR10-5T; CIFAR100-10T; CIFAR100-20T; T-ImageNet-5T; T-ImageNet-10T
Task: Image Classification -
Class-Wise Thresholding for Robust Out-of-Distribution Detection (CVPRw 2022) [Paper]
Datasets: Places365; SVHN; German Traffic Sign Recognition Benchmark (GTSRB); ImageNet; Anime Faces; Fishes; Fruits; iSUN; Jig-saw Training; LSUN; Office; PACS; Texture
Task: Image Classification -
PyTorch-OOD: A Library for Out-of-Distribution Detection Based on PyTorch (CVPRw 2022) [Paper] [Code]
Datasets: CIFAR 10 or CIFAR 100; ImageNet-A; ImageNet-O; Newsgroups; ImageNet-R
Task: Image Classification -
RODD: A Self-Supervised Approach for Robust Out-of-Distribution Detection (CVPRw 2022) [Paper] [Code]
Datasets: CIFAR-10 and CIFAR-100 as ID datasets and 7 OOD datasets. OOD datasets utilized are TinyImageNet-crop (TINc), TinyImageNet-resize(TINr), LSUN-resize (LSUN-r), Places, Textures, SVHN and iSUN
Task: Image Classification
- Addressing Out-of-Distribution Label Noise in Webly-Labelled Data (WACV 2022)
[Paper]
[Code]
Datasets: CIFAR-100, ImageNet32, MiniImageNet, Stanford Cars, mini-WebVision, ILSVRC12, Clothing1M
Task: Image Classification
-
OSM: An Open Set Matting Framework with OOD Detection and Few-Shot Matting (BMVC 2022) [Paper]
Datasets: SIMD
Task: Out-of-Distribution Detection, Semantic Image Matting -
VL4Pose: Active Learning Through Out-Of-Distribution Detection For Pose Estimation (BMVC 2022) [Paper] [Code]
Datasets: MPII, LSP/LSPET, ICVL
Task: Active Learning -
Shifting Transformation Learning for Robust Out-of-Distribution Detection (BMVC 2022) [Paper]
Datasets: CIFAR-10, CIFAR-100, ImageNet-30
Task: Image Classification
-
Deep Stable Learning for Out-of-Distribution Generalization (CVPR 2021) [Paper]
-
MOOD: Multi-Level Out-of-Distribution Detection (CVPR 2021) [Paper]
-
MOS: Towards Scaling Out-of-Distribution Detection for Large Semantic Space (CVPR 2021) [Paper]
-
Out-of-Distribution Detection Using Union of 1-Dimensional Subspaces (CVPR 2021) [Paper]
-
Multiscale Score Matching for Out-of-Distribution Detection (ICLR 2021) [Paper]
-
In-N-Out: Pre-Training and Self-Training using Auxiliary Information for Out-of-Distribution Robustness (ICLR 2021) [Paper]
-
Understanding the failure modes of out-of-distribution generalization (ICLR 2021) [Paper]
-
Removing Undesirable Feature Contributions Using Out-of-Distribution Data (ICLR 2021) [Paper]
-
Out-of-Distribution Generalization in Kernel Regression (NeurIPS 2021) [Paper]
-
Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalization (NeurIPS 2021) [Paper]
-
STEP: Out-of-Distribution Detection in the Presence of Limited In-Distribution Labeled Data (NeurIPS 2021) [Paper]
-
The Out-of-Distribution Problem in Explainability and Search Methods for Feature Importance Explanations (NeurIPS 2021) [Paper]
-
A Winning Hand: Compressing Deep Networks Can Improve Out-of-Distribution Robustness (NeurIPS 2021) [Paper]
-
Locally Most Powerful Bayesian Test for Out-of-Distribution Detection using Deep Generative Models (NeurIPS 2021) [Paper]
-
Task-Agnostic Undesirable Feature Deactivation Using Out-of-Distribution Data (NeurIPS 2021) [Paper]
-
Exploring the Limits of Out-of-Distribution Detection (NeurIPS 2021) [Paper]
-
ReAct: Out-of-distribution Detection With Rectified Activations (NeurIPS 2021) [Paper]
-
Learning Causal Semantic Representation for Out-of-Distribution Prediction (NeurIPS 2021) [Paper]
-
Towards a Theoretical Framework of Out-of-Distribution Generalization (NeurIPS 2021) [Paper]
-
Characterizing Generalization under Out-Of-Distribution Shifts in Deep Metric Learning (NeurIPS 2021) [Paper]
-
Single Layer Predictive Normalized Maximum Likelihood for Out-of-Distribution Detection (NeurIPS 2021) [Paper]
-
On the Out-of-distribution Generalization of Probabilistic Image Modelling (NeurIPS 2021) [Paper]
-
POODLE: Improving Few-shot Learning via Penalizing Out-of-Distribution Samples (NeurIPS 2021) [Paper]
-
Towards optimally abstaining from prediction with OOD test examples (NeurIPS 2021) [Paper]
-
Trash To Treasure: Harvesting OOD Data With Cross-Modal Matching for Open-Set Semi-Supervised Learning (ICCV 2021) [Paper]
Datasets: CIFAR-10, Animal-10, Tiny-ImageNet, CIFAR100
Task: Image Classification -
Entropy Maximization and Meta Classification for Out-of-Distribution Detection in Semantic Segmentation (ICCV 2021) [Paper]
-
The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization (ICCV 2021) [Paper]
-
MG-GAN: A Multi-Generator Model Preventing Out-of-Distribution Samples in Pedestrian Trajectory Prediction (ICCV 2021) [Paper]
-
Semantically Coherent Out-of-Distribution Detection (ICCV 2021) [Paper]
-
Linguistically Routing Capsule Network for Out-of-Distribution Visual Question Answering (ICCV 2021) [Paper]
-
CODEs: Chamfer Out-of-Distribution Examples Against Overconfidence Issue (ICCV 2021) [Paper]
-
NAS-OoD: Neural Architecture Search for Out-of-Distribution Generalization (ICCV 2021) [Paper]
-
Triggering Failures: Out-of-Distribution Detection by Learning From Local Adversarial Attacks in Semantic Segmentation (ICCV 2021) [Paper]
-
Understanding Failures in Out-of-Distribution Detection with Deep Generative Models (ICML 2021) [Paper]
-
Graph Convolution for Semi-Supervised Classification: Improved Linear Separability and Out-of-Distribution Generalization (ICML 2021) [Paper]
-
Out-of-Distribution Generalization via Risk Extrapolation (REx) (ICML 2021) [Paper]
-
Can Subnetwork Structure Be the Key to Out-of-Distribution Generalization? (ICML 2021) [Paper]
-
Accuracy on the Line: on the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization (ICML 2021) [Paper]
-
Amortized Conditional Normalized Maximum Likelihood: Reliable Out of Distribution Uncertainty Estimation (ICML 2021) [Paper]
-
Improved OOD Generalization via Adversarial Training and Pretraing (ICML 2021) [Paper]
-
Sample-Free White-Box Out-of-Distribution Detection for Deep Learning (CVPRw 2021) [Paper]
-
Out-of-Distribution Detection and Generation Using Soft Brownian Offset Sampling and Autoencoders (CVPRw 2021) [Paper]
-
DeVLBert: Out-of-Distribution Visio-Linguistic Pretraining With Causality (CVPRw 2021) [Paper]
- OODformer: Out-Of-Distribution Detection Transformer (BMVC 2021)
[Paper]
[Code]
Datasets: CIFAR-10/-100 and ImageNet30
Task: Image Classification
- SOoD: Self-Supervised Out-of-Distribution Detection Under Domain Shift for Multi-Class Colorectal Cancer Tissue Types (ICCVw 2021) [Paper]
- ATOM: Robustifying Out-of-distribution Detection Using Outlier Mining (ECML 2021) [Paper]
- Generalized ODIN: Detecting Out-of-Distribution Image Without Learning From Out-of-Distribution Data (CVPR 2020)
[Paper]
Datasets: CIFAR10, CIFAR100, SVHN, TinyImageNet, LSUN and iSUN, DomainNet
Task: Out-of-Distribution Image Classification
-
Input Complexity and Out-of-distribution Detection with Likelihood-based Generative Models (ICLR 2020) [Paper] [Code]
Datasets: CIFAR-10, CIFAR-100, CelebA, Fashion-MNIST, ImageNet, SVHN
Task: Out-of-Distribution Image Classification -
Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distribution Tasks (ICLR 2020 Oral) [Paper] [Code]
Datasets: CIFAR-10, CIFAR-100, CIFAR-FS, miniImageNet, SVHN, CUB, Aircraft, QuickDraw, and VGG-Flower, Traffic Signs, Fashion-MNIST
Task: Out-of-Distribution Image Classification
-
Why Normalizing Flows Fail to Detect Out-of-Distribution Data (NeurIPS 2020) [Paper]
-
Certifiably Adversarially Robust Detection of Out-of-Distribution Data (NeurIPS 2020) [Paper]
-
Likelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encoder (NeurIPS 2020) [Paper]
-
Towards Maximizing the Representation Gap between In-Domain & Out-of-Distribution Examples (NeurIPS 2020) [Paper]
-
Energy-based Out-of-distribution Detection (NeurIPS 2020) [Paper]
-
On the Value of Out-of-Distribution Testing: An Example of Goodhart's Law (NeurIPS 2020) [Paper]
-
OOD-MAML: Meta-Learning for Few-Shot Out-of-Distribution Detection and Classification (NeurIPS 2020) [Paper]
- Detecting Out-of-Distribution Examples with Gram Matrices (ICML 2020)
[Paper]
[Code]
Datasets: CIFAR10, CIFAR100, MNIST, SVHN, TinyImageNet, LSUN and iSUN
Task: Out-of-Distribution Image Classification
- A Boundary Based Out-of-Distribution Classifier for Generalized Zero-Shot Learning (ECCV 2020)
[Paper]
Datasets: AWA1, AWA2, CUB, FLO and SUN
Task: Out-of-Distribution Image Classification
-
On Out-of-Distribution Detection Algorithms With Deep Neural Skin Cancer Classifiers (CVPRw 2020) [Paper]
-
Detection and Retrieval of Out-of-Distribution Objects in Semantic Segmentation (CVPRw 2020) [Paper]
-
Enhancing the reliability of out-of-distribution image detection in neural networks (ICLR 2018) [Paper] [Code]
Datasets: CIFAR-10, CIFAR-100, ImageNet, iSUN
Task: Out-of-Distribution Image Classification -
A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks (NeurIPS 2018) [Paper] [Code]
Datasets: CIFAR, SVHN, ImageNet and LSUN
Task: Out-of-Distribution Image Classification -
Out-of-Distribution Detection using Multiple Semantic Label Representations (NeurIPS 2018) [Paper] [Code]
Datasets: CIFAR-10, CIFAR-100 and Google Speech Commands Dataset
Task: Out-of-Distribution Image, Speech Classification -
Likelihood Ratios for Out-of-Distribution Detection (NeurIPS 2019) [Paper]
Datasets: FashionMNIST -> MNIST, CIFAR10 -> SVHN, ImageNet and LSUN
Task: Out-of-Distribution Image Classification -
Out-of-Distribution Detection Using an Ensemble of Self Supervised Leave-out Classifiers (ECCV 2018) [Paper]
Datasets: CIFAR10, CIFAR100, TinyImageNet, LSUN, Uniform Noise(UNFM), Gaussian Noise(GSSN), iSUN
Task: Out-of-Distribution Image Classification -
Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples (ICLR 2018) [Paper] [Code]
Datasets: CIFAR-10, ImageNet, LSUN, MNIST, SVHN
Task: Out-of-Distribution Image Classification -
Unsupervised Out-of-Distribution Detection by Maximum Classifier Discrepancy (ICCV 2019) [Paper]
Datasets: CIFAR-10, CIFAR-100, LSUN, iSUN, TinyImageNet
Task: Out-of-Distribution Image Classification -
A Less Biased Evaluation of Out-of-distribution Sample Detectors (BMVC 2019) [Paper] [Code]
Datasets: CIFAR-10, CIFAR-100, MNIST, TinyImageNet, FashionMNIST, STL-10
Task: Out-of-Distribution Image Classification
- Towards Generalisable Video Moment Retrieval: Visual-Dynamic Injection to Image-Text Pre-Training (CVPR 2023) [Paper]
- Unknown-Aware Object Detection: Learning What You Don't Know From Videos in the Wild (CVPR 2022)
[Paper]
[Code]
Datasets: (Videos -> Images) BDD100K and Youtube-Video Instance Segmentation(Youtube-VIS) 2021 (ID) - MS-COCO and nuImages (OOD)
Task: Object Detection
-
Uncertainty-aware audiovisual activity recognition using deep bayesian variational inference (ICCV 2019) [Paper]
Datasets: MiT
Task: Audiovisual Action Recognition -
Bayesian activity recognition using variational inference (NeurIPS 2018) [Paper]
Datasets: MiT video activity recognition dataset
Task: Action Recognition -
Out-Of-Distribution Detection for Generalized Zero-Shot Action Recognition (CVPR 2019) [Paper] [Code]
Datasets: Olympic Sports, HMDB51 and UCF101
Task: Action Recognition