# Hyperdimensional Feature Fusion for Out-Of-Distribution Detection

arXiv: https://arxiv.org/abs/2112.05341 · HTML: https://mlsanity.com/paper/2112.05341/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 41 of its 65 references that are in the map.
- First posted on arXiv 10 Dec 2021.

## Builds on (most cited first, 30 of 41)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [Describing Textures in the Wild](https://mlsanity.com/paper/1311.3618/) (2013)
- [A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks](https://mlsanity.com/paper/1807.03888/) (2018)
- [LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop](https://mlsanity.com/paper/1506.03365/) (2015)
- [Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks](https://mlsanity.com/paper/1706.02690/) (2017)
- [Energy-based Out-of-distribution Detection](https://mlsanity.com/paper/2010.03759/) (2020)
- [Exact solutions to the nonlinear dynamics of learning in deep linear neural networks](https://mlsanity.com/paper/1312.6120/) (2013)
- [Large-Scale Long-Tailed Recognition in an Open World](https://mlsanity.com/paper/1904.05160/) (2019)
- [A Simple Baseline for Bayesian Uncertainty in Deep Learning](https://mlsanity.com/paper/1902.02476/) (2019)
- [ReAct: Out-of-distribution Detection With Rectified Activations](https://mlsanity.com/paper/2111.12797/) (2021)
- [Scaling Out-of-Distribution Detection for Real-World Settings](https://mlsanity.com/paper/1911.11132/) (2019)
- [Deep Learning for Classical Japanese Literature](https://mlsanity.com/paper/1812.01718/) (2018)
- [Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Data](https://mlsanity.com/paper/2002.11297/) (2020)
- [Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples](https://mlsanity.com/paper/1711.09325/) (2017)
- [Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem](https://mlsanity.com/paper/1812.05720/) (2018)
- [Learning Confidence for Out-of-Distribution Detection in Neural Networks](https://mlsanity.com/paper/1802.04865/) (2018)
- [Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learning](https://mlsanity.com/paper/1803.04765/) (2018)
- [A Simple Fix to Mahalanobis Distance for Improving Near-OOD Detection](https://mlsanity.com/paper/2106.09022/) (2021)
- [Deep Deterministic Uncertainty: A Simple Baseline](https://mlsanity.com/paper/2102.11582/) (2021)
- [Reducing Network Agnostophobia](https://mlsanity.com/paper/1811.04110/) (2018)
- [The Fishyscapes Benchmark: Measuring Blind Spots in Semantic Segmentation](https://mlsanity.com/paper/1904.03215/) (2019)
- [Unsupervised Out-of-Distribution Detection by Maximum Classifier Discrepancy](https://mlsanity.com/paper/1908.04951/) (2019)
- [Pixel-wise Anomaly Detection in Complex Driving Scenes](https://mlsanity.com/paper/2103.05445/) (2021)
- [The Limits and Potentials of Deep Learning for Robotics](https://mlsanity.com/paper/1804.06557/) (2018)
- [MOOD: Multi-level Out-of-distribution Detection](https://mlsanity.com/paper/2104.14726/) (2021)

## Built on by (most cited first, 13 of 13)

- [SAFE: Sensitivity-Aware Features for Out-of-Distribution Object Detection](https://mlsanity.com/paper/2208.13930/) (2022)
- [Non-Exemplar Online Class-incremental Continual Learning via Dual-prototype Self-augment and Refinement](https://mlsanity.com/paper/2303.10891/) (2023)
- [Image Labels Are All You Need for Coarse Seagrass Segmentation](https://mlsanity.com/paper/2303.00973/) (2023)
- [Hyperdimensional Uncertainty Quantification for Multimodal Uncertainty Fusion in Autonomous Vehicles Perception](https://mlsanity.com/paper/2503.20011/) (2025)
- [DOMINO: Domain-invariant Hyperdimensional Classification for Multi-Sensor Time Series Data](https://mlsanity.com/paper/2308.03295/) (2023)
- [Proto-OOD: Enhancing OOD Object Detection with Prototype Feature Similarity](https://mlsanity.com/paper/2409.05466/) (2024)
- [Efficient Model Adaptation for Continual Learning at the Edge](https://mlsanity.com/paper/2308.02084/) (2023)
- [SMORE: Similarity-based Hyperdimensional Domain Adaptation for Multi-Sensor Time Series Classification](https://mlsanity.com/paper/2402.13233/) (2024)
- [Learning with Local Gradients at the Edge](https://mlsanity.com/paper/2208.08503/) (2022)
- [A Hyperdimensional One Place Signature to Represent Them All: Stackable Descriptors For Visual Place Recognition](https://mlsanity.com/paper/2412.06153/) (2024)
- [Model-Agnostic Open-Set Air-to-Air Visual Object Detection for Reliable UAV Perception](https://mlsanity.com/paper/2509.09297/) (2025)
- [Large-Margin Hyperdimensional Computing: A Learning-Theoretical Perspective](https://mlsanity.com/paper/2603.03830/) (2026)
- [D2H-AD: A Hybrid Model Utilizing Hyperdimensional Computing for Advanced Anomaly Detection](https://mlsanity.com/paper/2606.13754/) (2026)

## Abstract (arXiv)

We introduce powerful ideas from Hyperdimensional Computing into the challenging field of Out-of-Distribution (OOD) detection. In contrast to most existing work that performs OOD detection based on only a single layer of a neural network, we use similarity-preserving semi-orthogonal projection matrices to project the feature maps from multiple layers into a common vector space. By repeatedly applying the bundling operation oplus, we create expressive class-specific descriptor vectors for all in-distribution classes. At test time, a simple and efficient cosine similarity calculation between descriptor vectors consistently identifies OOD samples with better performance than the current state-of-the-art. We show that the hyperdimensional fusion of multiple network layers is critical to achieve best general performance.