MHLR: Moving Haar Learning Rate Scheduler for Large-scale Face Recognition Training with One GPU

no code implementations • 17 Apr 2024 • Xueyuan Gong, Yain-Whar Si, Zheng Zhang, Xiaochen Yuan, Ke Wang, Xinyuan Zhang, Cong Lin, Xiaoxiang Liu

MHLR supports large-scale FR training with only one GPU, which is able to accelerate the model to 1/4 of its original training time without sacrificing more than 1% accuracy.

Face Recognition Scheduling

X2-Softmax: Margin Adaptive Loss Function for Face Recognition

no code implementations • 8 Dec 2023 • Jiamu Xu, Xiaoxiang Liu, Xinyuan Zhang, Yain-Whar Si, Xiaofan Li, Zheng Shi, Ke Wang, Xueyuan Gong

Learning the discriminative features of different faces is an important task in face recognition.

Face Recognition

KDCTime: Knowledge Distillation with Calibration on InceptionTime for Time-series Classification

no code implementations • 4 Dec 2021 • Xueyuan Gong, Yain-Whar Si, Yongqi Tian, Cong Lin, Xinyuan Zhang, Xiaoxiang Liu

Time-series classification approaches based on deep neural networks are easy to be overfitting on UCR datasets, which is caused by the few-shot problem of those datasets.

Knowledge Distillation Time Series +2

Multi-source Transfer Learning with Ensemble for Financial Time Series Forecasting

no code implementations • 26 Mar 2021 • Qi-Qiao He, Patrick Cheong-Iao Pang, Yain-Whar Si

Majority of existing works on transfer learning are based on single-source transfer learning due to the availability of open-access large-scale datasets.

Time Series Time Series Forecasting +1