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

arXiv: https://arxiv.org/abs/2012.04250 · HTML: https://mlsanity.com/paper/2012.04250/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Dec 2020.

## Built on by (most cited first, 20 of 20)

- [ViM: Out-Of-Distribution with Virtual-logit Matching](https://mlsanity.com/paper/2203.10807/) (2022)
- [CLIPN for Zero-Shot OOD Detection: Teaching CLIP to Say No](https://mlsanity.com/paper/2308.12213/) (2023)
- [Fast Decision Boundary based Out-of-Distribution Detector](https://mlsanity.com/paper/2312.11536/) (2023)
- [Simplicity Bias in 1-Hidden Layer Neural Networks](https://mlsanity.com/paper/2302.00457/) (2023)
- [Class Incremental Learning via Likelihood Ratio Based Task Prediction](https://mlsanity.com/paper/2309.15048/) (2023)
- [Pursuing Feature Separation based on Neural Collapse for Out-of-Distribution Detection](https://mlsanity.com/paper/2405.17816/) (2024)
- [EPA: Neural Collapse Inspired Robust Out-of-Distribution Detector](https://mlsanity.com/paper/2401.01710/) (2024)
- [WDiscOOD: Out-of-Distribution Detection via Whitened Linear Discriminant Analysis](https://mlsanity.com/paper/2303.07543/) (2023)
- [Low-Dimensional Gradient Helps Out-of-Distribution Detection](https://mlsanity.com/paper/2310.17163/) (2023)
- [MOODv2: Masked Image Modeling for Out-of-Distribution Detection](https://mlsanity.com/paper/2401.02611/) (2024)
- [COOD: Combined out-of-distribution detection using multiple measures for anomaly & novel class detection in large-scale hierarchical classification](https://mlsanity.com/paper/2403.06874/) (2024)
- [Equipping Vision Foundation Model with Mixture of Experts for Out-of-Distribution Detection](https://mlsanity.com/paper/2510.10584/) (2025)
- [CUAL: Continual Uncertainty-aware Active Learner](https://mlsanity.com/paper/2412.09701/) (2024)
- [Uncertainty Quantification in Continual Open-World Learning](https://mlsanity.com/paper/2412.16409/) (2024)
- [DisCoPatch: Taming Adversarially-driven Batch Statistics for Improved Out-of-Distribution Detection](https://mlsanity.com/paper/2501.08005/) (2025)
- [Kernel PCA for Out-of-Distribution Detection: Non-Linear Kernel Selection and Approximation](https://mlsanity.com/paper/2505.15284/) (2025)
- [Dimensionality-induced information loss of outliers in deep neural networks](https://mlsanity.com/paper/2410.21656/) (2024)
- [CONCLAD: COntinuous Novel CLAss Detector](https://mlsanity.com/paper/2412.10473/) (2024)
- [The Invisible Gorilla Effect in Out-of-distribution Detection](https://mlsanity.com/paper/2602.20068/) (2026)
- [MaRS: Robust Out-of-Distribution Detection via Mahalanobis Residual Scoring](https://mlsanity.com/paper/2606.22649/) (2026)

## Abstract (arXiv)

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 L2-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.