# Out-of-distribution Detection with Boundary Aware Learning

arXiv: https://arxiv.org/abs/2112.11648 · HTML: https://mlsanity.com/paper/2112.11648/

## 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 (most cited first, 27 of 27)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [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)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [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)
- [Deep Anomaly Detection with Outlier Exposure](https://mlsanity.com/paper/1812.04606/) (2018)
- [Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images](https://mlsanity.com/paper/1412.1897/) (2014)
- [Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty](https://mlsanity.com/paper/1906.12340/) (2019)
- [Likelihood Ratios for Out-of-Distribution Detection](https://mlsanity.com/paper/1906.02845/) (2019)
- [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)
- [On the Importance of Gradients for Detecting Distributional Shifts in the Wild](https://mlsanity.com/paper/2110.00218/) (2021)
- [FastText.zip: Compressing text classification models](https://mlsanity.com/paper/1612.03651/) (2016)
- [Learning Confidence for Out-of-Distribution Detection in Neural Networks](https://mlsanity.com/paper/1802.04865/) (2018)
- [Contrastive Training for Improved Out-of-Distribution Detection](https://mlsanity.com/paper/2007.05566/) (2020)
- [Robust Classification with Convolutional Prototype Learning](https://mlsanity.com/paper/1805.03438/) (2018)
- [Improving Reconstruction Autoencoder Out-of-distribution Detection with Mahalanobis Distance](https://mlsanity.com/paper/1812.02765/) (2018)
- [Out-of-distribution Detection in Classifiers via Generation](https://mlsanity.com/paper/1910.04241/) (2019)
- [Detecting Out-of-Distribution Examples with In-distribution Examples and Gram Matrices](https://mlsanity.com/paper/1912.12510/) (2019)
- [Out-of-Distribution Detection using Multiple Semantic Label Representations](https://mlsanity.com/paper/1808.06664/) (2018)
- [Detecting Out-of-Distribution Inputs in Deep Neural Networks Using an Early-Layer Output](https://mlsanity.com/paper/1910.10307/) (2019)

## Built on by (most cited first, 11 of 11)

- [Out-of-Distribution Detection for Monocular Depth Estimation](https://mlsanity.com/paper/2308.06072/) (2023)
- [Out-of-Distribution Detection with Prototypical Outlier Proxy](https://mlsanity.com/paper/2412.16884/) (2024)
- [BOOD: Boundary-based Out-Of-Distribution Data Generation](https://mlsanity.com/paper/2508.00350/) (2025)
- [Image Background Serves as Good Proxy for Out-of-distribution Data](https://mlsanity.com/paper/2307.00519/) (2023)
- [Hierarchical Point-Patch Fusion with Adaptive Patch Codebook for 3D Shape Anomaly Detection](https://mlsanity.com/paper/2604.03972/) (2026)
- [Thinking in Groups: Permutation Tests Reveal Near-Out-of-Distribution](https://mlsanity.com/paper/2403.14058/) (2024)
- [Free Lunch for Generating Effective Outlier Supervision](https://mlsanity.com/paper/2301.06657/) (2023)
- [Incremental Object-Based Novelty Detection with Feedback Loop](https://mlsanity.com/paper/2311.09004/) (2023)
- [PLOOD: Partial Label Learning with Out-of-distribution Objects](https://mlsanity.com/paper/2403.06681/) (2024)
- [phepy: Visual benchmarks and improvements for out-of-distribution detectors](https://mlsanity.com/paper/2503.05169/) (2025)
- [Sharpness-Aware Geometric Defense for Robust Out-Of-Distribution Detection](https://mlsanity.com/paper/2508.17174/) (2025)

## 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.