Pith. sign in

REVIEW 13 cited by

Generalized Out-of-Distribution Detection: A Survey

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2110.11334 v3 pith:LCS2R4U6 submitted 2021-10-21 cs.CV cs.AIcs.LG

Jingkang Yang , Kaiyang Zhou , Yixuan Li , Ziwei Liu This is my paper · ORCID
classification cs.CVcs.AIcs.LG
keywords detectionfiveproblemssurveydrivingfirstframeworkgeneralized
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Out-of-distribution (OOD) detection is critical to ensuring the reliability and safety of machine learning systems. For instance, in autonomous driving, we would like the driving system to issue an alert and hand over the control to humans when it detects unusual scenes or objects that it has never seen during training time and cannot make a safe decision. The term, OOD detection, first emerged in 2017 and since then has received increasing attention from the research community, leading to a plethora of methods developed, ranging from classification-based to density-based to distance-based ones. Meanwhile, several other problems, including anomaly detection (AD), novelty detection (ND), open set recognition (OSR), and outlier detection (OD), are closely related to OOD detection in terms of motivation and methodology. Despite common goals, these topics develop in isolation, and their subtle differences in definition and problem setting often confuse readers and practitioners. In this survey, we first present a unified framework called generalized OOD detection, which encompasses the five aforementioned problems, i.e., AD, ND, OSR, OOD detection, and OD. Under our framework, these five problems can be seen as special cases or sub-tasks, and are easier to distinguish. We then review each of these five areas by summarizing their recent technical developments, with a special focus on OOD detection methodologies. We conclude this survey with open challenges and potential research directions.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 13 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. TOOD: Task-Aware Out-of-Distribution Score Calibration for Continual Learners

    cs.CV 2026-07 conditional novelty 6.0 of 10

    OOD detection in continual learning degrades through task-dependent logit-scale drift and feature-space crowding; a post-hoc per-task energy calibration recovers most of that loss for energy-based detectors.

  2. Variational Inference for Evidential Deep Learning

    cs.LG 2026-05 unverdicted novelty 6.0 of 10

    VI-EDL trains evidential classifiers with a full Dirichlet KL penalty and a cosine prototype layer, reporting gains in OOD detection but grounding its theory in a flawed ELBO derivation.

  3. Scaling K2 VIII: Short-Period Sub-Neptune Occurrence Rates Peak Around Early-Type M Dwarfs

    astro-ph.EP 2025-08 unverdicted novelty 6.0 of 10

    Short-period sub-Neptunes peak at about 3750 K around early-type M dwarfs, matching pebble accretion predictions, while super-Earths keep rising toward cooler stars.

  4. Invariant Link Selector for Spatial-Temporal Out-of-Distribution Problem

    cs.LG 2025-05 reject novelty 6.0 of 10

    OOD-Linker selects invariant links in temporal graphs via an information-bottleneck objective and reports a generalization error bound and link-prediction experiments under distribution shift.

  5. NMINE: Normalized Mutual Information Neural Estimation

    cs.LG 2026-07 conditional novelty 5.0 of 10

    A fully neural estimator for normalized mutual information beats a KSG baseline on Gaussian data but fails to deliver its advertised scale-invariance property.

  6. Rare Event Analysis of Large Language Models

    cs.LG 2026-02 conditional novelty 5.0 of 10

    Using annealed transition path sampling plus MBAR reweighting, the authors estimate TinyStories-8M completion probabilities for extreme ARI and log-probability values that are unobservable by direct sampling.

  7. Energy Landscapes Enable Reliable Abstention in Retrieval-Augmented Large Language Models for Healthcare

    cs.CL 2025-08 conditional novelty 5.0 of 10

    An energy-based scoring head trained on dense embeddings improves abstention decisions for medical RAG systems on semantically hard out-of-distribution queries compared to softmax and kNN baselines.

  8. Enclosing Prototypical Variational Autoencoder for Explainable Out-of-Distribution Detection

    cs.LG 2025-06 conditional novelty 5.0 of 10

    A prototype-based variational autoencoder with a generalized-Gaussian restriction loss and perceptual reconstruction detects out-of-distribution images better than prior methods on some benchmarks, especially low-dive...

  9. Feature Bank Enhancement for Distance-based Out-of-Distribution Detection

    cs.LG 2025-07 conditional novelty 4.0 of 10

    Clipping per-dimension outlier features in the training feature bank improves distance-based out-of-distribution detection on ImageNet-1k and CIFAR-10.

  10. Enhancing Abnormality Identification: Robust Out-of-Distribution Strategies for Deepfake Detection

    cs.CV 2025-06 conditional novelty 4.0 of 10

    The paper introduces a deepfake OOD detector that combines reconstruction residual, latent encoding, and softmax confidence, and shows strong results only when real OOD samples are available for training.

  11. SpectralGap: Graph-Level Out-of-Distribution Detection via Laplacian Eigenvalue Gaps

    cs.LG 2025-05 conditional novelty 4.0 of 10

    SpecGap adjusts GNN features by subtracting the second-largest Laplacian eigenvector component times the spectral gap, claiming improved graph OOD detection without retraining.

  12. Entropy-Based Non-Invasive Reliability Monitoring of Convolutional Neural Networks

    cs.CV 2025-08 reject novelty 3.0 of 10

    A CNN's activation entropy separates clean from FGSM-attacked image batches in a small VGG-16 test, but fitted binning, tiny samples, and contradictory numbers weaken the claim.

  13. Large Language Models for Crash Detection in Video: A Survey of Methods, Datasets, and Challenges

    cs.CV 2025-07 conditional novelty 3.0 of 10

    A structured survey of 2023-2025 LLM and VLM methods for crash detection in video, with notable internal inconsistencies in reported numbers.

Pith tools