计算机科学
水准点(测量)
判别式
聚类分析
人工智能
模式识别(心理学)
鉴定(生物学)
相似性(几何)
星团(航天器)
依赖关系(UML)
路径(计算)
无监督学习
机器学习
数据挖掘
图像(数学)
植物
大地测量学
生物
程序设计语言
地理
作者
Zhenyu Liu,Jiawei Lian,Jiahua Wu,Da‐Han Wang,Yun Wu,Shunzhi Zhu,Dewu Ge
标识
DOI:10.1007/978-981-99-8462-6_17
摘要
Most existing unsupervised re-identification uses a clustering-based approach to generate pseudo-labels as supervised signals, allowing deep neural networks to learn discriminative representations without annotations. However, drawbacks in clustering algorithms and the absence of discriminatory ability early in training limit better performance seriously. A severe problem arises from path dependency, wherein noisy samples rarely have a chance to escape from their assigned clusters during iterative training. To tackle this challenge, we propose a novel label refinement strategy based on the stable cluster reconstruction. Our approach contains two modules, the stable cluster reconstruction (SCR) module and the similarity recalculate (SR) module. It reconstructs more stable clusters and re-evaluates the relationship between samples and clearer cluster representatives, providing complementary information for pseudo labels at the instance level. Our proposed approach effectively improves unsupervised reID performance, achieving state-of-the-art performance on four benchmark datasets. Specifically, our method achieves 46.0% and 39.1% mAP on the challenging dataset VeRi776 and MSMT17.
科研通智能强力驱动
Strongly Powered by AbleSci AI