QGait: Toward Accurate Quantization for Gait Recognition with Binarized Input

Existing deep learning methods have made significant progress in gait recognition. Typically, appearance-based models binarize inputs into silhouette sequences. However, mainstream quantization methods prioritize minimizing task loss over quantization error, which is detrimental to gait recognition...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2024-05
Hauptverfasser:	Tian, Senmao, Gao, Haoyu, Hong, Gangyi, Wang, Shuyun, Wang, JingJie, Yu, Xin, Zhang, Shunli
Format:	Artikel
Sprache:	eng
Schlagworte:	Back propagation Convergence Distillation Empirical analysis Errors Gait recognition
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!