Pith. sign in

REVIEW 27 cited by

Not yet reviewed by Pith; the record is open.

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 1706.02690 v5 pith:KT3B2YO2 submitted 2017-06-08 cs.LG stat.ML

Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks

classification cs.LG stat.ML
keywords neuralodinout-of-distributionbaselinedetectioneffectiveimagesmethod
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

We consider the problem of detecting out-of-distribution images in neural networks. We propose ODIN, a simple and effective method that does not require any change to a pre-trained neural network. Our method is based on the observation that using temperature scaling and adding small perturbations to the input can separate the softmax score distributions between in- and out-of-distribution images, allowing for more effective detection. We show in a series of experiments that ODIN is compatible with diverse network architectures and datasets. It consistently outperforms the baseline approach by a large margin, establishing a new state-of-the-art performance on this task. For example, ODIN reduces the false positive rate from the baseline 34.7% to 4.3% on the DenseNet (applied to CIFAR-10) when the true positive rate is 95%.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 27 Pith papers

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

  1. Geometric Measurements of the Axiom of Choice in Neural Proof Embeddings

    cs.LG 2026-06 unverdicted novelty 7.0

    Proofs depending on the axiom of choice show a geometric signature in neural embeddings of tactic sequences that weakens with dependency-graph distance and correlates with prover failure rates.

  2. Uncertainty Estimation via Hyperspherical Confidence Mapping

    cs.LG 2026-05 unverdicted novelty 7.0

    HCM turns neural outputs into magnitude plus unit hypersphere vector and treats uncertainty as the geometric violation of that unit constraint, yielding deterministic estimates for regression and classification that m...

  3. CURE-OOD: Benchmarking Out-of-Distribution Detection for Survival Prediction

    cs.CV 2026-05 unverdicted novelty 7.0

    CURE-OOD is the first benchmark for evaluating OOD detection in survival prediction under controlled CT acquisition shifts, showing that standard detectors often fail and providing a survival-aware baseline.

  4. Sparsity as a Key: Unlocking New Insights from Latent Structures for Out-of-Distribution Detection

    cs.CV 2026-04 unverdicted novelty 7.0

    Sparse autoencoders on ViT class tokens reveal stable Class Activation Profiles for in-distribution data, enabling OOD detection via divergence from core energy profiles.

  5. SLE-FNO: Single-Layer Extensions for Task-Agnostic Continual Learning in Fourier Neural Operators

    cs.LG 2026-03 unverdicted novelty 7.0

    SLE-FNO achieves zero forgetting and strong plasticity-stability balance in continual learning for FNO surrogate models of pulsatile blood flow by adding minimal single-layer extensions across four out-of-distribution tasks.

  6. Catching Disguised Transients with ASTRANet: Anomaly-Aware Spectroscopic Classification and Conformal Calibration

    astro-ph.IM 2026-07 conditional novelty 6.0

    ASTRANet combines a redshift-free spectral classifier, a 16-score anomaly detector, and conformal prediction to identify and calibrate uncertainty for out-of-taxonomy astronomical transients.

  7. When Confidence Lacks Concepts: Interpretable OOD Detection via Representation Perturbations

    cs.LG 2026-06 unverdicted novelty 6.0

    Proposes using sparse autoencoders to extract class-conditioned concept vectors, then measuring logit stability under targeted perturbations as an interpretable OOD signal for deep networks in medical imaging.

  8. Debiased Negative Mining Improves Out-of-distribution Detection with Pre-trained Vision-Language Models

    cs.LG 2026-05 unverdicted novelty 6.0

    Debiased negative mining via Monte-Carlo sampling from ID labels and unlabeled wild data improves OOD detection with VLMs and achieves new state-of-the-art results.

  9. Random-Set Graph Neural Networks

    cs.AI 2026-05 unverdicted novelty 6.0

    RS-GNNs predict random sets over classes using belief functions to jointly produce class probabilities and epistemic uncertainty estimates for graph nodes.

  10. Domain Restriction via Multi SAE Layer Transitions

    cs.AI 2026-05 unverdicted novelty 6.0

    Multi-layer SAE transitions capture domain-specific signatures that distinguish OOD texts in Gemma-2 models.

  11. Uncertainty Estimation via Hyperspherical Confidence Mapping

    cs.LG 2026-05 unverdicted novelty 6.0

    HCM estimates uncertainty in neural network outputs by quantifying violation of a unit hypersphere constraint on the normalized direction vector.

  12. Don't Collapse Your Features: Why CenterLoss Hurts OOD Detection and Multi-Scale Mahalanobis Wins

    cs.LG 2026-04 conditional novelty 6.0

    Avoiding CenterLoss improves OOD detection via multi-scale Mahalanobis on L2-normalized features, yielding 0.9483 AUROC on CIFAR-10 while preserving competitive in-distribution accuracy.

  13. ConjNorm: Tractable Density Estimation for Out-of-Distribution Detection

    cs.LG 2024-02 unverdicted novelty 6.0

    ConjNorm reframes OOD detection score design as optimizing norm p in an exponential family density model via a Bregman divergence theorem, with a tractable Monte Carlo estimator, claiming SOTA gains on CIFAR-100 and I...

  14. PointCaM: Cut-and-Mix for Open-Set Point Cloud Learning

    cs.CV 2022-12 unverdicted novelty 6.0

    PointCaM proposes a cut-and-mix mechanism with an Unknown-Point Simulator and Estimator to improve open-set recognition on point clouds by simulating out-of-distribution data and using multi-level features.

  15. Language Models (Mostly) Know What They Know

    cs.CL 2022-07 unverdicted novelty 6.0

    Language models show good calibration when asked to estimate the probability that their own answers are correct, with performance improving as models get larger.

  16. Dual Feature Decoupling for Fine-Grained OOD Detection

    cs.CV 2026-06 unverdicted novelty 5.0

    DFDNet disentangles content from style via dual modules to boost fine-grained OOD detection performance on multiple datasets.

  17. Learning Hyperspherical Time-Frequency Representations for Time-Series Out-of-Distribution Detection

    cs.LG 2026-05 unverdicted novelty 5.0

    Hyperspherical time-frequency representations learned via von Mises-Fisher likelihood improve OOD detection on UCR and UEA archives using k-NN and Mahalanobis scores over contrastive baselines.

  18. Three-Step Conditional Diffusion 3D Reconstruction for Light-Field Microscopy

    cs.CV 2026-05 unverdicted novelty 5.0

    Proposes TCD, a three-step conditional diffusion model with ICD module, claiming superior fidelity and generalization for LFM 3D reconstruction.

  19. Enhancing Deep Neural Network Reliability with Refinement and Calibration

    cs.LG 2026-05 unverdicted novelty 5.0

    RefCal uses a supervised contrastive loss to promote refinement alongside calibration in DNN training, reporting better accuracy, refinement, and ECE than baselines on imbalanced CIFAR-100-LT.

  20. UniAlign: A Model-Agnostic Framework for Robust Network Traffic Classification under Distribution Shifts

    cs.LG 2026-05 unverdicted novelty 5.0

    UniAlign improves robustness of deep learning NTC models under distribution shifts via domain alignment fine-tuning and stable ensembling, yielding 2.51% accuracy and 2.71% F1 gains over standard training on three pub...

  21. HEDP: A Hybrid Energy-Distance Prompt-based Framework for Domain Incremental Learning

    cs.AI 2026-05 unverdicted novelty 5.0

    HEDP uses energy regularization inspired by Helmholtz free energy plus hybrid energy-distance weighting in prompts to improve domain selection and achieve a 2.57% accuracy gain on benchmarks like CORe50 while mitigati...

  22. Out of Distribution Detection in Self-adaptive Robots with AI-powered Digital Twins

    cs.RO 2025-09 unverdicted novelty 5.0

    ODiSAR uses a Transformer digital twin with reconstruction error and Monte Carlo dropout to detect OOD events in self-adaptive robots, reporting up to 98% AUROC on office navigation and maritime ship tasks.

  23. Benchmarking Vision Foundation Models for Input Monitoring in Autonomous Driving

    cs.CV 2025-01 unverdicted novelty 5.0

    Vision foundation model embeddings with density modeling outperform state-of-the-art methods for unsupervised semantic and covariate shift detection in autonomous driving inputs.

  24. Metamorphic Testing of a Deep Learning based Forecaster

    cs.LG 2019-07 unverdicted novelty 5.0

    Developed 19 metamorphic relations to test correlation detection and LSTM forecasting in an outage prediction application, uncovering 8 unknown issues in the live system and detecting 65.9% of injected bugs via mutati...

  25. AEGIS: A Semantic GAN and Evidential Learning Frameworkfor Robust Adversarial Detection in Vision Sensors

    cs.CV 2026-06 unverdicted novelty 4.0

    AEGIS combines SemantiGAN filtering with evidential learning on five handcrafted instability metrics to detect adversarial attacks, reporting 92.1% AUROC on Tiny ImageNet across six attack types.

  26. Out-of-Distribution (OOD) Detectors for Open-Set RF Fingerprinting

    cs.LG 2026-06 unverdicted novelty 4.0

    Applies OOD detectors to open-set RF fingerprinting via an information-theoretic framework and demonstrates effective tuning without OOD data on the POWDER dataset.

  27. Beyond Toy Benchmarks: A Systematic Evaluation of OOD Detection Methods For Plant Pathology Classification

    cs.CV 2026-05 unverdicted novelty 4.0

    Energy-based fine-tuning outperforms other OOD detection methods on the real-world Plant Pathology 2021 dataset, improving detection over softmax while maintaining in-distribution accuracy.