mlsanityData to 7 Oct 2026

Dual Representation Learning for Out-of-Distribution Detection

arXiv 2206.09387 ↗First posted 19 Jun 2022cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

To classify in-distribution samples, deep neural networks explore strongly label-related information and discard weakly label-related information according to the information bottleneck. Out-of-distribution samples drawn from distributions differing from that of in-distribution samples could be assigned with unexpected high-confidence predictions because they could obtain minimum strongly label-related information. To distinguish in- and out-of-distribution samples, Dual Representation Learning (DRL) makes out-of-distribution samples harder to have high-confidence predictions by exploring both strongly and weakly label-related information from in-distribution samples. For a pretrained network exploring strongly label-related information to learn label-discriminative representations, DRL trains its auxiliary network exploring the remaining weakly label-related information to learn distribution-discriminative representations. Specifically, for a label-discriminative representation, DRL constructs its complementary distribution-discriminative representation by integrating diverse representations less similar to the label-discriminative representation. Accordingly, DRL combines label- and distribution-discriminative representations to detect out-of-distribution samples. Experiments show that DRL outperforms the state-of-the-art methods for out-of-distribution detection.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 39 of its 61 references that are in the map. First posted on arXiv 19 Jun 2022.

Builds on

39 of 61 references.

References · 39

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  5. 2016Densely Connected Convolutional Networkscited by 6,691
  6. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  7. 2017On Calibration of Modern Neural Networkscited by 4,860
  8. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  9. 2014Going Deeper with Convolutionscited by 4,231
  10. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  11. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  12. 2013Describing Textures in the Wildcited by 2,110
27 more
  1. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  2. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
  3. 2020Energy-based Out-of-distribution Detectioncited by 1,296
  4. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 918
  5. 2016Deep Variational Information Bottleneckcited by 915
  6. 2018MINE: Mutual Information Neural Estimationcited by 680
  7. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 596
  8. 2018Predictive Uncertainty Estimation via Prior Networkscited by 555
  9. 2019Using Self-Supervised Learning Can Improve Model Robustness and Uncertaintycited by 511
  10. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
  11. 2019Likelihood Ratios for Out-of-Distribution Detectioncited by 451
  12. 2020CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instancescited by 441
  13. 2020Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Datacited by 408
  14. 2017Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samplescited by 389
  15. 2019Using Pre-Training Can Improve Model Robustness and Uncertaintycited by 373
  16. 2021MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Spacecited by 233
  17. 2020Learning Robust Representations via Multi-View Information Bottleneckcited by 189
  18. 2020Contrastive Training for Improved Out-of-Distribution Detectioncited by 186
  19. 2022How to Exploit Hyperspherical Embeddings for Out-of-Distribution Detection?cited by 128
  20. 2020Hybrid Models for Open Set Recognitioncited by 109
  21. 2021Provable Guarantees for Understanding Out-of-distribution Detectioncited by 78
  22. 2016Monte Carlo Markov Chain Algorithms for Sampling Strongly Rayleigh Distributions and Determinantal Point Processescited by 24
  23. 2018Out-of-Distribution Detection using Multiple Semantic Label Representationscited by 22
  24. 2021Revealing the Distributional Vulnerability of Discriminators by Implicit Generatorscited by 10
  25. 2021Evolving Decomposed Plasticity Rules for Information-Bottlenecked Meta-Learningcited by 5
  26. 2016Multi-way Monte Carlo Method for Linear Systemscited by 3
  27. 2022VFDS: Variational Foresight Dynamic Selection in Bayesian Neural Networks for Efficient Human Activity Recognitioncited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 1; 2025: 0; 2026: 1.

4 papers.

  1. 2023Diversifying Spatial-Temporal Perception for Video Domain Generalizationcited by 19
  2. 2026What Information Matters? Graph Out-of-Distribution Detection via Tri-Component Information Decompositioncited by 1
  3. 2023Distilling the Unknown to Unveil Certaintycited by 0
  4. 2024Double Descent Meets Out-of-Distribution Detection: Theoretical Insights and Empirical Analysis on the role of model complexitycited by 0