How to Achieve Prototypical Birth and Death for OOD Detection?

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Peng, Ningkang, Yu, Qianfeng, Peng, Xiaoqian, Qian, Linjing, Liu, Yafei, Xiao, Canran, Lu, Xinyu, Lu, Tingyu, Zheng, Zhichao, Gu, Yanhui
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908890876084224
author Peng, Ningkang
Yu, Qianfeng
Peng, Xiaoqian
Qian, Linjing
Liu, Yafei
Xiao, Canran
Lu, Xinyu
Lu, Tingyu
Zheng, Zhichao
Gu, Yanhui
author_facet Peng, Ningkang
Yu, Qianfeng
Peng, Xiaoqian
Qian, Linjing
Liu, Yafei
Xiao, Canran
Lu, Xinyu
Lu, Tingyu
Zheng, Zhichao
Gu, Yanhui
contents Out-of-Distribution (OOD) detection is crucial for the secure deployment of machine learning models, and prototype-based learning methods are among the mainstream strategies for achieving OOD detection. Existing prototype-based learning methods generally rely on a fixed number of prototypes. This static assumption fails to adapt to the inherent complexity differences across various categories. Currently, there is still a lack of a mechanism that can adaptively adjust the number of prototypes based on data complexity. Inspired by the processes of cell birth and death in biology, we propose a novel method named PID (Prototype bIrth and Death) to adaptively adjust the prototype count based on data complexity. This method relies on two dynamic mechanisms during the training process: prototype birth and prototype death. The birth mechanism instantiates new prototypes in data regions with insufficient representation by identifying the overload level of existing prototypes, thereby meticulously capturing intra-class substructures. Conversely, the death mechanism reinforces the decision boundary by pruning prototypes with ambiguous class boundaries through evaluating their discriminability. Through birth and death, the number of prototypes can be dynamically adjusted according to the data complexity, leading to the learning of more compact and better-separated In-Distribution (ID) embeddings, which significantly enhances the capability to detect OOD samples. Experiments demonstrate that our dynamic method, PID, significantly outperforms existing methods on benchmarks such as CIFAR-100, achieving State-of-the-Art (SOTA) performance, especially on the FPR95 metric.
format Preprint
id arxiv_https___arxiv_org_abs_2603_15650
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle How to Achieve Prototypical Birth and Death for OOD Detection?
Peng, Ningkang
Yu, Qianfeng
Peng, Xiaoqian
Qian, Linjing
Liu, Yafei
Xiao, Canran
Lu, Xinyu
Lu, Tingyu
Zheng, Zhichao
Gu, Yanhui
Machine Learning
Computer Vision and Pattern Recognition
Out-of-Distribution (OOD) detection is crucial for the secure deployment of machine learning models, and prototype-based learning methods are among the mainstream strategies for achieving OOD detection. Existing prototype-based learning methods generally rely on a fixed number of prototypes. This static assumption fails to adapt to the inherent complexity differences across various categories. Currently, there is still a lack of a mechanism that can adaptively adjust the number of prototypes based on data complexity. Inspired by the processes of cell birth and death in biology, we propose a novel method named PID (Prototype bIrth and Death) to adaptively adjust the prototype count based on data complexity. This method relies on two dynamic mechanisms during the training process: prototype birth and prototype death. The birth mechanism instantiates new prototypes in data regions with insufficient representation by identifying the overload level of existing prototypes, thereby meticulously capturing intra-class substructures. Conversely, the death mechanism reinforces the decision boundary by pruning prototypes with ambiguous class boundaries through evaluating their discriminability. Through birth and death, the number of prototypes can be dynamically adjusted according to the data complexity, leading to the learning of more compact and better-separated In-Distribution (ID) embeddings, which significantly enhances the capability to detect OOD samples. Experiments demonstrate that our dynamic method, PID, significantly outperforms existing methods on benchmarks such as CIFAR-100, achieving State-of-the-Art (SOTA) performance, especially on the FPR95 metric.
title How to Achieve Prototypical Birth and Death for OOD Detection?
topic Machine Learning
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.15650