Pith. sign in

REVIEW 6 cited by

Out-Of-Distribution Detection With Subspace Techniques And Probabilistic Modeling Of Features

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 2012.04250 v1 pith:GRYUPQEV submitted 2020-12-08 cs.LG

classification cs.LG
keywords featuresfeaturedetectioneffectivesubspacetechniquesapproachdeep
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

This paper presents a principled approach for detecting out-of-distribution (OOD) samples in deep neural networks (DNN). Modeling probability distributions on deep features has recently emerged as an effective, yet computationally cheap method to detect OOD samples in DNN. However, the features produced by a DNN at any given layer do not fully occupy the corresponding high-dimensional feature space. We apply linear statistical dimensionality reduction techniques and nonlinear manifold-learning techniques on the high-dimensional features in order to capture the true subspace spanned by the features. We hypothesize that such lower-dimensional feature embeddings can mitigate the curse of dimensionality, and enhance any feature-based method for more efficient and effective performance. In the context of uncertainty estimation and OOD, we show that the log-likelihood score obtained from the distributions learnt on this lower-dimensional subspace is more discriminative for OOD detection. We also show that the feature reconstruction error, which is the $L_2$-norm of the difference between the original feature and the pre-image of its embedding, is highly effective for OOD detection and in some cases superior to the log-likelihood scores. The benefits of our approach are demonstrated on image features by detecting OOD images, using popular DNN architectures on commonly used image datasets such as CIFAR10, CIFAR100, and SVHN.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 6 Pith papers

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

  1. Multimodal Classification and Out-of-distribution Detection for Multimodal Intent Understanding

    cs.MM 2024-12 conditional novelty 6.0 of 10

    MIntOOD mixes synthetic out-of-distribution features from multiple known intent classes and learns weighted multimodal fusion with binary, cosine-classifier, and contrastive losses, improving OOD AUROC by 2.5 to 8.4 p...

  2. CONCLAD: COntinuous Novel CLAss Detector

    cs.LG 2024-12 conditional novelty 6.0 of 10

    CONCLAD combines iterative PCA-based uncertainty scores, a small active-labeling budget, and pseudo-labeling to continuously separate and learn multiple novel classes from old classes.

  3. Uncertainty Quantification in Continual Open-World Learning

    cs.LG 2024-12 conditional novelty 5.0 of 10

    COUQ iteratively combines old-class and novel-class feature reconstruction errors to produce uncertainty scores that stay reliable as new classes arrive, improving continual novelty detection and active learning.

  4. CUAL: Continual Uncertainty-aware Active Learner

    cs.LG 2024-12 conditional novelty 5.0 of 10

    CUAL combines ambiguity-based active querying with confidence-filtered pseudo-labeling so a continual learner can handle unlabeled streams containing both old and novel classes under a tiny labeling budget.

  5. Kernel PCA for Out-of-Distribution Detection: Non-Linear Kernel Selection and Approximation

    cs.LG 2025-05 conditional novelty 4.0 of 10

    Out-of-distribution images are detected by the reconstruction error of a Cosine-Gaussian kernel PCA subspace learned from in-distribution features.

  6. SAFE: Self-Supervised Anomaly Detection Framework for Intrusion Detection

    cs.CR 2025-02 conditional novelty 4.0 of 10

    SAFE combines PCA feature ranking, DeepInsight tabular-to-image conversion, masked autoencoder pretraining, and Local Outlier Factor to detect network intrusions without attack labels.

Pith tools