# Out-of-Distribution Detection with Prototypical Outlier Proxy

arXiv: https://arxiv.org/abs/2412.16884 · HTML: https://mlsanity.com/paper/2412.16884/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 39 references that are in the map.
- First posted on arXiv 22 Dec 2024.

## Builds on (most cited first, 26 of 26)

- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [Describing Textures in the Wild](https://mlsanity.com/paper/1311.3618/) (2013)
- [A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks](https://mlsanity.com/paper/1807.03888/) (2018)
- [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)
- [End-to-End Training of Deep Visuomotor Policies](https://mlsanity.com/paper/1504.00702/) (2015)
- [Prevalence of Neural Collapse during the terminal phase of deep learning training](https://mlsanity.com/paper/2008.08186/) (2020)
- [Out-of-Distribution Detection with Deep Nearest Neighbors](https://mlsanity.com/paper/2204.06507/) (2022)
- [End-to-end Autonomous Driving: Challenges and Frontiers](https://mlsanity.com/paper/2306.16927/) (2023)
- [ViM: Out-Of-Distribution with Virtual-logit Matching](https://mlsanity.com/paper/2203.10807/) (2022)
- [VOS: Learning What You Don't Know by Virtual Outlier Synthesis](https://mlsanity.com/paper/2202.01197/) (2022)
- [In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluation](https://mlsanity.com/paper/2306.00826/) (2023)
- [Unsupervised Out-of-Distribution Detection by Maximum Classifier Discrepancy](https://mlsanity.com/paper/1908.04951/) (2019)
- [POEM: Out-of-Distribution Detection with Posterior Sampling](https://mlsanity.com/paper/2206.13687/) (2022)
- [Semantically Coherent Out-of-Distribution Detection](https://mlsanity.com/paper/2108.11941/) (2021)
- [Places: An Image Database for Deep Scene Understanding](https://mlsanity.com/paper/1610.02055/) (2016)
- [Mixture Outlier Exposure: Towards Out-of-Distribution Detection in Fine-grained Environments](https://mlsanity.com/paper/2106.03917/) (2021)
- [On the Principles of Parsimony and Self-Consistency for the Emergence of Intelligence](https://mlsanity.com/paper/2207.04630/) (2022)
- [Fix your classifier: the marginal value of training the last weight layer](https://mlsanity.com/paper/1801.04540/) (2018)
- [Learning Hierarchy Aware Features for Reducing Mistake Severity](https://mlsanity.com/paper/2207.12646/) (2022)
- [Inducing Neural Collapse to a Fixed Hierarchy-Aware Frame for Reducing Mistake Severity](https://mlsanity.com/paper/2303.05689/) (2023)
- [Out-of-distribution Detection with Boundary Aware Learning](https://mlsanity.com/paper/2112.11648/) (2021)

## Built on by (most cited first, 4 of 4)

- [LoRA-BAM: Input Filtering for Fine-tuned LLMs via Boxed Abstraction Monitors over LoRA Layers](https://mlsanity.com/paper/2506.00998/) (2025)
- [Learning with Adaptive Prototype Manifolds for Out-of-Distribution Detection](https://mlsanity.com/paper/2602.05349/) (2026)
- [ALOOD: Exploiting Language Representations for LiDAR-based Out-of-Distribution Object Detection](https://mlsanity.com/paper/2603.08180/) (2026)
- [DynProto: Dynamic Prototype Evolution for Out-of-Distribution Detection](https://mlsanity.com/paper/2604.23729/) (2026)

## Abstract (arXiv)

Out-of-distribution (OOD) detection is a crucial task for deploying deep learning models in the wild. One of the major challenges is that well-trained deep models tend to perform over-confidence on unseen test data. Recent research attempts to leverage real or synthetic outliers to mitigate the issue, which may significantly increase computational costs and be biased toward specific outlier characteristics. In this paper, we propose a simple yet effective framework, Prototypical Outlier Proxy (POP), which introduces virtual OOD prototypes to reshape the decision boundaries between ID and OOD data. Specifically, we transform the learnable classifier into a fixed one and augment it with a set of prototypical weight vectors. Then, we introduce a hierarchical similarity boundary loss to impose adaptive penalties depending on the degree of misclassification. Extensive experiments across various benchmarks demonstrate the effectiveness of POP. Notably, POP achieves average FPR95 reductions of 7.70%, 6.30%, and 5.42% over the second-best methods on CIFAR-10, CIFAR-100, and ImageNet-200, respectively. Moreover, compared to the recent method NPOS, which relies on outlier synthesis, POP trains 7.2X faster and performs inference 19.5X faster. The source code is available at: https://github.com/gmr523/pop.