A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is
In this paper, we resolve this problem by incorporating a Parametric Sigmoid Norm (PSN) layer just before the final fully-connected layer. We propose a PSNet CNN model by using the PSN layer. ... It is also used over widely studied face recognition problem. However, the existing layers of CNN are unable to cope with the problem of hard examples which generally produce lower class scores. ... It can lead to a better light weight CNN model for resource constrained devices. Fig. 1 . 1 The proposed PSNet CNN model for face recognition with Parametric-Sigmoid-Norm (PSN) layer represented. ...arXiv:1912.10946v1 fatcat:4e5javrquzhfvcwmyzdrscf4ai
2019 IEEE Conference on Information and Communication Technology
of Multitasking in Divided Attention using Machine Learning 61 135 PID6226089 Yash Srivastava, Vaishnav Murali and Shiv Ram Dubey PSNet: Parametric Sigmoid Norm Based CNN for Face Recognition ... descriptor for Human Action Recognition from Depth Sequences 28 75 PID6312503 Raghav Gahlot, Nitish Andola, Rakhi Verma, S. ...doi:10.1109/cict48419.2019.9066118 fatcat:f4gjbv6v5fbcnkzquhc2a2ho2e