mlsanityData to 14 Oct 2026

Out-of-Distribution Detection via Channelwise Feature Aggregation in Neural Network-Based Receivers

arXiv 2505.15570 ↗First posted 21 May 2025cs.LG eess.SPcited by 0

Not on the map. Why?

Abstract (arXiv)

Neural network-based radio receivers are expected to play a key role in future wireless systems, making reliable Out-Of-Distribution (OOD) detection essential. We propose a post-hoc, layerwise OOD framework based on channelwise feature aggregation that avoids classwise statistics--critical for multi-label soft-bit outputs with astronomically many classes. Receiver activations exhibit no discrete clusters but a smooth Signal-to-Noise-Ratio (SNR)-aligned manifold, consistent with classical receiver behavior and motivating manifold-aware OOD detection. We evaluate multiple OOD feature types, distance metrics, and methods across layers. Gaussian Mahalanobis with mean activations is the strongest single detector, earlier layers outperform later, and SNR/classifier fusions offer small, inconsistent AUROC gains. High-delay OOD is detected reliably, while high-speed remains challenging.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 44 of its 124 references that are in the map. First posted on arXiv 21 May 2025.

Builds on

44 of 124 references.

References · 44

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  4. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  5. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  6. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,898
  7. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
  8. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,332
  9. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,329
  10. 2013Visualizing and Understanding Convolutional Networkscited by 2,290
  11. 2019Similarity of Neural Network Representations Revisitedcited by 1,755
  12. 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,319
32 more
  1. 2020Energy-based Out-of-distribution Detectioncited by 1,299
  2. 2022Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 smallcited by 1,165
  3. 2021Generalized Out-of-Distribution Detection: A Surveycited by 802
  4. 2017Network Dissection: Quantifying Interpretability of Deep Visual Representationscited by 708
  5. 2017Interpretable Explanations of Black Boxes by Meaningful Perturbationcited by 612
  6. 2019Using Self-Supervised Learning Can Improve Model Robustness and Uncertaintycited by 514
  7. 2015Understanding Neural Networks Through Deep Visualizationcited by 334
  8. 2020Understanding the Role of Individual Units in a Deep Neural Networkcited by 255
  9. 2018Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learningcited by 207
  10. 2025Open Problems in Mechanistic Interpretabilitycited by 179
  11. 2020Debugging Tests for Model Explanationscited by 147
  12. 2022Sionna: An Open-Source Library for Next-Generation Physical Layer Researchcited by 145
  13. 2022Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networkscited by 129
  14. 2017Accelerated Hierarchical Density Clusteringcited by 102
  15. 2021Can multi-label classification networks know what they don't know?cited by 100
  16. 2020Toward a 6G AI-Native Air Interfacecited by 55
  17. 2016AdaNet: Adaptive Structural Learning of Artificial Neural Networkscited by 54
  18. 2020DeepRx: Fully Convolutional Deep Learning Receivercited by 52
  19. 2025Controlling Large Language Models Through Concept Activation Vectorscited by 28
  20. 2022Human-Centered Concept Explanations for Neural Networkscited by 23
  21. 2024Deep Learning for Multi-Label Learning: A Comprehensive Surveycited by 19
  22. 2020Out-of-Distribution Detection in Multi-Label Datasets using Latent Space of β-VAEcited by 15
  23. 2020DeepRx MIMO: Convolutional MIMO Detection with Learned Multiplicative Transformationscited by 14
  24. 2024From A-to-Z Review of Clustering Validation Indicescited by 11
  25. 2023Concept Distillation: Leveraging Human-Centered Explanations for Model Improvementcited by 10
  26. 2022Concept-Based Explanations for Tabular Datacited by 4
  27. 2024Adapting to Reality: Over-the-Air Validation of AI-Based Receivers Trained with Simulated Channelscited by 3
  28. 2025Robust Deep Learning-Based Physical Layer Communications: Strategies and Approachescited by 3
  29. 2024Asynchronous Online Adaptation via Modular Drift Detection for Deep Receiverscited by 2
  30. 2024Interpreting Deep Neural Network-Based Receiver Under Varying Signal-To-Noise Ratioscited by 2
  31. 2020Using Channel State Information for Physical Tamper Attack Detection in OFDM Systems: A Deep Learning Approachcited by 1
  32. 2025Multi-label out-of-distribution detection via evidential learningcited by 1

Built on by

Not cited yet.