cs.AI updates on arXiv.org 20小时前
CatEquiv:基于对称性的动作识别神经网络
index_new5.html
../../../zaker_core/zaker_tpl_static/wap/tpl_guoji1.html

 

本文提出CatEquiv,一种用于从惯性传感器进行人体活动识别的神经网络,系统性地编码时间、幅度和结构对称性。CatEquiv通过引入对称性类别,联合表示周期性时间平移、正增益缩放和传感器层次偏序,捕捉数据的分类对称结构。实验表明,CatEquiv在UCI-HAR数据集上,相较于循环填充CNN和平坦CNN,具有更高的鲁棒性。

arXiv:2511.01139v2 Announce Type: cross Abstract: We propose CatEquiv, a category-equivariant neural network for Human Activity Recognition (HAR) from inertial sensors that systematically encodes temporal, amplitude, and structural symmetries. We introduce a symmetry category that jointly represents cyclic time shifts, positive gain scalings, and the sensor-hierarchy poset, capturing the categorical symmetry structure of the data. CatEquiv achieves equivariance with respect to the categorical symmetry product. On UCI-HAR under out-of-distribution perturbations, CatEquiv attains markedly higher robustness compared with circularly padded CNNs and plain CNNs. These results demonstrate that enforcing categorical symmetries yields strong invariance and generalization without additional model capacity.

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

CatEquiv 人体活动识别 神经网络 对称性 鲁棒性
相关文章