mlsanityData to 7 Oct 2026

Hyperdimensional Feature Fusion for Out-Of-Distribution Detection

arXiv 2112.05341 ↗First posted 10 Dec 2021cs.CV cs.AIcited by 13

Not on the map. Why?

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.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 41 of its 65 references that are in the map. First posted on arXiv 10 Dec 2021.

Builds on

41 of 65 references.

References · 41

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  3. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  4. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  5. 2016Wide Residual Networkscited by 3,057
  6. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  7. 2013Describing Textures in the Wildcited by 2,110
  8. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  9. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  10. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
  11. 2020Energy-based Out-of-distribution Detectioncited by 1,296
  12. 2013Exact solutions to the nonlinear dynamics of learning in deep linear neural networkscited by 748
29 more
  1. 2019Large-Scale Long-Tailed Recognition in an Open Worldcited by 704
  2. 2019A Simple Baseline for Bayesian Uncertainty in Deep Learningcited by 555
  3. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
  4. 2019Scaling Out-of-Distribution Detection for Real-World Settingscited by 465
  5. 2018Deep Learning for Classical Japanese Literaturecited by 415
  6. 2020Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Datacited by 408
  7. 2017Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samplescited by 389
  8. 2018Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problemcited by 323
  9. 2018Learning Confidence for Out-of-Distribution Detection in Neural Networkscited by 245
  10. 2021A Simple Fix to Mahalanobis Distance for Improving Near-OOD Detectioncited by 206
  11. 2018Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learningcited by 203
  12. 2021Deep Deterministic Uncertainty: A Simple Baselinecited by 200
  13. 2018Reducing Network Agnostophobiacited by 165
  14. 2019The Fishyscapes Benchmark: Measuring Blind Spots in Semantic Segmentationcited by 122
  15. 2019Unsupervised Out-of-Distribution Detection by Maximum Classifier Discrepancycited by 112
  16. 2021Pixel-wise Anomaly Detection in Complex Driving Scenescited by 109
  17. 2018The Limits and Potentials of Deep Learning for Roboticscited by 104
  18. 2021MOOD: Multi-level Out-of-distribution Detectioncited by 94
  19. 2020A comparison of Vector Symbolic Architecturescited by 63
  20. 2020Classification using Hyperdimensional Computing: A Reviewcited by 60
  21. 2019Simultaneous Semantic Segmentation and Outlier Detection in Presence of Domain Shiftcited by 54
  22. 2020Feature Space Singularity for Out-of-Distribution Detectioncited by 49
  23. 2021Neural Mean Discrepancy for Efficient Out-of-Distribution Detectioncited by 42
  24. 2021Uncertainty for Identifying Open-Set Errors in Visual Object Detectioncited by 26
  25. 2015Representing Objects, Relations, and Sequencescited by 24
  26. 2020Detection and Retrieval of Out-of-Distribution Objects in Semantic Segmentationcited by 20
  27. 2019Did You Miss the Sign? A False Negative Alarm System for Traffic Sign Detectorscited by 14
  28. 2020The Hidden Uncertainty in a Neural Networks Activationscited by 14
  29. 2020Online Monitoring of Object Detection Performance During Deploymentcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 4; 2024: 3; 2025: 2; 2026: 2.

13 papers.

Sort:

  1. 2022SAFE: Sensitivity-Aware Features for Out-of-Distribution Object Detectioncited by 33
  2. 2023Non-Exemplar Online Class-incremental Continual Learning via Dual-prototype Self-augment and Refinementcited by 13
  3. 2023Image Labels Are All You Need for Coarse Seagrass Segmentationcited by 7
  4. 2025Hyperdimensional Uncertainty Quantification for Multimodal Uncertainty Fusion in Autonomous Vehicles Perceptioncited by 6
  5. 2023DOMINO: Domain-invariant Hyperdimensional Classification for Multi-Sensor Time Series Datacited by 5
  6. 2024Proto-OOD: Enhancing OOD Object Detection with Prototype Feature Similaritycited by 4
  7. 2023Efficient Model Adaptation for Continual Learning at the Edgecited by 3
  8. 2024SMORE: Similarity-based Hyperdimensional Domain Adaptation for Multi-Sensor Time Series Classificationcited by 3
  9. 2022Learning with Local Gradients at the Edgecited by 1
  10. 2024A Hyperdimensional One Place Signature to Represent Them All: Stackable Descriptors For Visual Place Recognitioncited by 1
  11. 2025Model-Agnostic Open-Set Air-to-Air Visual Object Detection for Reliable UAV Perceptioncited by 1
  12. 2026Large-Margin Hyperdimensional Computing: A Learning-Theoretical Perspectivecited by 1
1 more
  1. 2026D2H-AD: A Hybrid Model Utilizing Hyperdimensional Computing for Advanced Anomaly Detectioncited by 0