mlsanityData to 14 Oct 2026

Out-of-distribution Detection with Boundary Aware Learning

arXiv 2112.11648 ↗First posted 22 Dec 2021cs.CVcited by 11

Not on the map. Why?

Abstract (arXiv)

There is an increasing need to determine whether inputs are out-of-distribution (OOD) for safely deploying machine learning models in the open world scenario. Typical neural classifiers are based on the closed world assumption, where the training data and the test data are drawn i.i.d. from the same distribution, and as a result, give over-confident predictions even faced with OOD inputs. For tackling this problem, previous studies either use real outliers for training or generate synthetic OOD data under strong assumptions, which are either costly or intractable to generalize. In this paper, we propose boundary aware learning (BAL), a novel framework that can learn the distribution of OOD features adaptively. The key idea of BAL is to generate OOD features from trivial to hard progressively with a generator, meanwhile, a discriminator is trained for distinguishing these synthetic OOD features and in-distribution (ID) features. Benefiting from the adversarial training scheme, the discriminator can well separate ID and OOD features, allowing more robust OOD detection. The proposed BAL achieves state-of-the-art performance on classification benchmarks, reducing up to 13.9% FPR95 compared with previous methods.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 27 of its 38 references that are in the map. First posted on arXiv 22 Dec 2021.

Builds on

27 of 38 references.

References · 27

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  3. 2016Densely Connected Convolutional Networkscited by 6,720
  4. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  5. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  6. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  7. 2016Concrete Problems in AI Safetycited by 1,642
  8. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
  9. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,355
  10. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,328
  11. 2020Energy-based Out-of-distribution Detectioncited by 1,299
  12. 2018Deep Anomaly Detection with Outlier Exposurecited by 942
15 more
  1. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 776
  2. 2019Using Self-Supervised Learning Can Improve Model Robustness and Uncertaintycited by 514
  3. 2019Likelihood Ratios for Out-of-Distribution Detectioncited by 453
  4. 2020Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Datacited by 408
  5. 2017Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samplescited by 389
  6. 2021On the Importance of Gradients for Detecting Distributional Shifts in the Wildcited by 339
  7. 2016FastText.zip: Compressing text classification modelscited by 335
  8. 2018Learning Confidence for Out-of-Distribution Detection in Neural Networkscited by 245
  9. 2020Contrastive Training for Improved Out-of-Distribution Detectioncited by 186
  10. 2018Robust Classification with Convolutional Prototype Learningcited by 123
  11. 2018Improving Reconstruction Autoencoder Out-of-distribution Detection with Mahalanobis Distancecited by 74
  12. 2019Out-of-distribution Detection in Classifiers via Generationcited by 49
  13. 2019Detecting Out-of-Distribution Examples with In-distribution Examples and Gram Matricescited by 32
  14. 2018Out-of-Distribution Detection using Multiple Semantic Label Representationscited by 22
  15. 2019Detecting Out-of-Distribution Inputs in Deep Neural Networks Using an Early-Layer Outputcited by 20

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 4; 2024: 3; 2025: 3; 2026: 1.

11 papers.

  1. 2023Out-of-Distribution Detection for Monocular Depth Estimationcited by 7
  2. 2024Out-of-Distribution Detection with Prototypical Outlier Proxycited by 4
  3. 2025BOOD: Boundary-based Out-Of-Distribution Data Generationcited by 4
  4. 2023Image Background Serves as Good Proxy for Out-of-distribution Datacited by 3
  5. 2026Hierarchical Point-Patch Fusion with Adaptive Patch Codebook for 3D Shape Anomaly Detectioncited by 3
  6. 2024Thinking in Groups: Permutation Tests Reveal Near-Out-of-Distributioncited by 1
  7. 2023Free Lunch for Generating Effective Outlier Supervisioncited by 0
  8. 2023Incremental Object-Based Novelty Detection with Feedback Loopcited by 0
  9. 2024PLOOD: Partial Label Learning with Out-of-distribution Objectscited by 0
  10. 2025phepy: Visual benchmarks and improvements for out-of-distribution detectorscited by 0
  11. 2025Sharpness-Aware Geometric Defense for Robust Out-Of-Distribution Detectioncited by 0