# Proto-OOD: Enhancing OOD Object Detection with Prototype Feature Similarity

arXiv: https://arxiv.org/abs/2409.05466 · HTML: https://mlsanity.com/paper/2409.05466/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 38 references that are in the map.
- First posted on arXiv 9 Sep 2024.

## Builds on (most cited first, 30 of 32)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks](https://mlsanity.com/paper/1807.03888/) (2018)
- [Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks](https://mlsanity.com/paper/1706.02690/) (2017)
- [Learning to Compare: Relation Network for Few-Shot Learning](https://mlsanity.com/paper/1711.06025/) (2017)
- [Out-of-Distribution Detection with Deep Nearest Neighbors](https://mlsanity.com/paper/2204.06507/) (2022)
- [DETRs Beat YOLOs on Real-time Object Detection](https://mlsanity.com/paper/2304.08069/) (2023)
- [CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances](https://mlsanity.com/paper/2007.08176/) (2020)
- [Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Data](https://mlsanity.com/paper/2002.11297/) (2020)
- [ViM: Out-Of-Distribution with Virtual-logit Matching](https://mlsanity.com/paper/2203.10807/) (2022)
- [Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples](https://mlsanity.com/paper/1711.09325/) (2017)
- [VOS: Learning What You Don't Know by Virtual Outlier Synthesis](https://mlsanity.com/paper/2202.01197/) (2022)
- [A Simple Fix to Mahalanobis Distance for Improving Near-OOD Detection](https://mlsanity.com/paper/2106.09022/) (2021)
- [End-to-end Learning of Driving Models from Large-scale Video Datasets](https://mlsanity.com/paper/1612.01079/) (2016)
- [Non-Parametric Outlier Synthesis](https://mlsanity.com/paper/2303.02966/) (2023)
- [Unsupervised Out-of-Distribution Detection by Maximum Classifier Discrepancy](https://mlsanity.com/paper/1908.04951/) (2019)
- [Infinite Mixture Prototypes for Few-Shot Learning](https://mlsanity.com/paper/1902.04552/) (2019)
- [Dream the Impossible: Outlier Imagination with Diffusion Models](https://mlsanity.com/paper/2309.13415/) (2023)
- [Out-of-distribution Detection in Classifiers via Generation](https://mlsanity.com/paper/1910.04241/) (2019)
- [Feature Space Singularity for Out-of-Distribution Detection](https://mlsanity.com/paper/2011.14654/) (2020)
- [Neural Mean Discrepancy for Efficient Out-of-Distribution Detection](https://mlsanity.com/paper/2104.11408/) (2021)
- [Multiscale Score Matching for Out-of-Distribution Detection](https://mlsanity.com/paper/2010.13132/) (2020)
- [SAFE: Sensitivity-Aware Features for Out-of-Distribution Object Detection](https://mlsanity.com/paper/2208.13930/) (2022)
- [Building robust classifiers through generation of confident out of distribution examples](https://mlsanity.com/paper/1812.00239/) (2018)
- [Detecting Out-of-Distribution Inputs in Deep Neural Networks Using an Early-Layer Output](https://mlsanity.com/paper/1910.10307/) (2019)
- [Contrastive Prototype Learning with Augmented Embeddings for Few-Shot Learning](https://mlsanity.com/paper/2101.09499/) (2021)
- [Prototypical VoteNet for Few-Shot 3D Point Cloud Object Detection](https://mlsanity.com/paper/2210.05593/) (2022)

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

- [Out-of-Distribution Detection: A Task-Oriented Survey of Recent Advances](https://mlsanity.com/paper/2409.11884/) (2024)
- [Multi-Cache Enhanced Prototype Learning for Test-Time Generalization of Vision-Language Models](https://mlsanity.com/paper/2508.01225/) (2025)
- [Few-Shot Learning in Video and 3D Object Detection: A Survey](https://mlsanity.com/paper/2507.17079/) (2025)
- [MD-ProTector: Positioning Multiple Data-Driven Prototypes for LLM-Generated Text Detection](https://mlsanity.com/paper/2608.10459/) (2026)

## Abstract (arXiv)

Neural networks that are trained on limited category samples often mispredict out-of-distribution (OOD) objects. We observe that features of the same category are more tightly clustered in feature space, while those of different categories are more dispersed. Based on this, we propose using prototype similarity for OOD detection. Drawing on widely used prototype features in few-shot learning, we introduce a novel OOD detection network structure (Proto-OOD). Proto-OOD enhances the representativeness of category prototypes using contrastive loss and detects OOD data by evaluating the similarity between input features and category prototypes. During training, Proto-OOD generates OOD samples for training the similarity module with a negative embedding generator. When Pascal VOC are used as the in-distribution dataset and MS-COCO as the OOD dataset, Proto-OOD significantly reduces the FPR (false positive rate). Moreover, considering the limitations of existing evaluation metrics, we propose a more reasonable evaluation protocol. The code will be released.