cs.AI updates on arXiv.org 08月01日 12:08
Mitigating Resolution-Drift in Federated Learning: Case of Keypoint Detection
index_new5.html
../../../zaker_core/zaker_tpl_static/wap/tpl_guoji1.html

 

本文探讨了联邦学习在非分类任务,如人体姿态估计中的应用,并提出了一种名为RAF的解决方案,通过多分辨率知识蒸馏技术有效缓解分辨率漂移问题,并证明其在现有框架中的可集成性。

arXiv:2507.23461v1 Announce Type: cross Abstract: The Federated Learning (FL) approach enables effective learning across distributed systems, while preserving user data privacy. To date, research has primarily focused on addressing statistical heterogeneity and communication efficiency, through which FL has achieved success in classification tasks. However, its application to non-classification tasks, such as human pose estimation, remains underexplored. This paper identifies and investigates a critical issue termed ``resolution-drift,'' where performance degrades significantly due to resolution variability across clients. Unlike class-level heterogeneity, resolution drift highlights the importance of resolution as another axis of not independent or identically distributed (non-IID) data. To address this issue, we present resolution-adaptive federated learning (RAF), a method that leverages heatmap-based knowledge distillation. Through multi-resolution knowledge distillation between higher-resolution outputs (teachers) and lower-resolution outputs (students), our approach enhances resolution robustness without overfitting. Extensive experiments and theoretical analysis demonstrate that RAF not only effectively mitigates resolution drift and achieves significant performance improvements, but also can be integrated seamlessly into existing FL frameworks. Furthermore, although this paper focuses on human pose estimation, our t-SNE analysis reveals distinct characteristics between classification and high-resolution representation tasks, supporting the generalizability of RAF to other tasks that rely on preserving spatial detail.

Fish AI Reader

Fish AI Reader

AI辅助创作,多种专业模板,深度分析,高质量内容生成。从观点提取到深度思考,FishAI为您提供全方位的创作支持。新版本引入自定义参数,让您的创作更加个性化和精准。

FishAI

FishAI

鱼阅,AI 时代的下一个智能信息助手,助你摆脱信息焦虑

联系邮箱 441953276@qq.com

相关标签

联邦学习 分辨率漂移 知识蒸馏 人体姿态估计
相关文章