# Unsupervised Out-of-Distribution Detection by Maximum Classifier Discrepancy

arXiv: https://arxiv.org/abs/1908.04951 · HTML: https://mlsanity.com/paper/1908.04951/

## Key facts

- Cited by 112 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Aug 2019.

## Built on by (most cited first, 30 of 112)

- [Generalized Out-of-Distribution Detection: A Survey](https://mlsanity.com/paper/2110.11334/) (2021)
- [A Survey of Uncertainty in Deep Neural Networks](https://mlsanity.com/paper/2107.03342/) (2021)
- [ViM: Out-Of-Distribution with Virtual-logit Matching](https://mlsanity.com/paper/2203.10807/) (2022)
- [OpenOOD: Benchmarking Generalized Out-of-Distribution Detection](https://mlsanity.com/paper/2210.07242/) (2022)
- [OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detection](https://mlsanity.com/paper/2306.09301/) (2023)
- [A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challenges](https://mlsanity.com/paper/2110.14051/) (2021)
- [A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learning](https://mlsanity.com/paper/2205.13218/) (2022)
- [Semantically Coherent Out-of-Distribution Detection](https://mlsanity.com/paper/2108.11941/) (2021)
- [LoCoOp: Few-Shot Out-of-Distribution Detection via Prompt Learning](https://mlsanity.com/paper/2306.01293/) (2023)
- [SoTTA: Robust Test-Time Adaptation on Noisy Data Streams](https://mlsanity.com/paper/2310.10074/) (2023)
- [Rethinking Reconstruction Autoencoder-Based Out-of-Distribution Detection](https://mlsanity.com/paper/2203.02194/) (2022)
- [NGC: A Unified Framework for Learning with Open-World Noisy Data](https://mlsanity.com/paper/2108.11035/) (2021)
- [Outlier detection by ensembling uncertainty with negative objectness](https://mlsanity.com/paper/2402.15374/) (2024)
- [Detection and Continual Learning of Novel Face Presentation Attacks](https://mlsanity.com/paper/2108.12081/) (2021)
- [SAFE: Sensitivity-Aware Features for Out-of-Distribution Object Detection](https://mlsanity.com/paper/2208.13930/) (2022)
- [Learning on Graphs with Out-of-Distribution Nodes](https://mlsanity.com/paper/2308.06714/) (2023)
- [Taxonomy of Machine Learning Safety: A Survey and Primer](https://mlsanity.com/paper/2106.04823/) (2021)
- [DIVERSIFY: A General Framework for Time Series Out-of-distribution Detection and Generalization](https://mlsanity.com/paper/2308.02282/) (2023)
- [UMAD: Universal Model Adaptation under Domain and Category Shift](https://mlsanity.com/paper/2112.08553/) (2021)
- [Out-of-Distribution Detection with Semantic Mismatch under Masking](https://mlsanity.com/paper/2208.00446/) (2022)
- [Interpretable Self-Aware Neural Networks for Robust Trajectory Prediction](https://mlsanity.com/paper/2211.08701/) (2022)
- [Your Data Is Not Perfect: Towards Cross-Domain Out-of-Distribution Detection in Class-Imbalanced Data](https://mlsanity.com/paper/2412.06284/) (2024)
- [How Useful are Gradients for OOD Detection Really?](https://mlsanity.com/paper/2205.10439/) (2022)
- [Robust Semi-supervised Learning by Wisely Leveraging Open-set Data](https://mlsanity.com/paper/2405.06979/) (2024)
- [Uncertainty-Aware Optimal Transport for Semantically Coherent Out-of-Distribution Detection](https://mlsanity.com/paper/2303.10449/) (2023)
- [Unified Entropy Optimization for Open-Set Test-Time Adaptation](https://mlsanity.com/paper/2404.06065/) (2024)
- [MCDAL: Maximum Classifier Discrepancy for Active Learning](https://mlsanity.com/paper/2107.11049/) (2021)
- [The Devil is in the Wrongly-classified Samples: Towards Unified Open-set Recognition](https://mlsanity.com/paper/2302.04002/) (2023)
- [Unleashing Mask: Explore the Intrinsic Out-of-Distribution Detection Capability](https://mlsanity.com/paper/2306.03715/) (2023)
- [Curved Geometric Networks for Visual Anomaly Recognition](https://mlsanity.com/paper/2208.01188/) (2022)

## Abstract (arXiv)

Since deep learning models have been implemented in many commercial applications, it is important to detect out-of-distribution (OOD) inputs correctly to maintain the performance of the models, ensure the quality of the collected data, and prevent the applications from being used for other-than-intended purposes. In this work, we propose a two-head deep convolutional neural network (CNN) and maximize the discrepancy between the two classifiers to detect OOD inputs. We train a two-head CNN consisting of one common feature extractor and two classifiers which have different decision boundaries but can classify in-distribution (ID) samples correctly. Unlike previous methods, we also utilize unlabeled data for unsupervised training and we use these unlabeled data to maximize the discrepancy between the decision boundaries of two classifiers to push OOD samples outside the manifold of the in-distribution (ID) samples, which enables us to detect OOD samples that are far from the support of the ID samples. Overall, our approach significantly outperforms other state-of-the-art methods on several OOD detection benchmarks and two cases of real-world simulation.