Smooth Maximum Unit: Smooth Activation Function for Deep Networks using Smoothing Maximum Technique-Reference-Cited by-同舟云学术

Smooth Maximum Unit: Smooth Activation Function for Deep Networks using Smoothing Maximum Technique

Published:2022-06 Issue: Volume: Page:
ISSN:
Container-title:2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
language:
Short-container-title:

Author:

Biswas Koushik¹,Kumar Sandeep¹,Banerjee Shilpak²,Pandey Ashish Kumar¹

Affiliation:

1. IIIT Delhi

2. IIT Tirupati

Publisher

IEEE

Link

http://xplorestaging.ieee.org/ielx7/9878378/9878366/09878772.pdf?arnumber=9878772

Reference56 articles.

1. Scalable parallel programming

2. Maas, Awni Y. Hannun, and Andrew Y. Ng. Rectifier nonlinearities improve neural network acoustic models;andrew;ICML Workshop on Deep Learning for Audio Speech and Language Processing,2013

Cited by 24 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. NCANet: Integrating Normalized Channel Attention for Enhanced Lightweight Image Classification;2024-09-13

2. A smooth maximum regularization approach for robust topology optimization in the ground structure setting;Structural and Multidisciplinary Optimization;2024-07-30

3. RSC-WSRGAN super-resolution reconstruction based on improved generative adversarial network;Signal, Image and Video Processing;2024-07-18

4. Investigating Robustness of Trainable Activation Functions for End-to-end Deep Learning Model in Autonomous Vehicles;2024 Fifteenth International Conference on Ubiquitous and Future Networks (ICUFN);2024-07-02

5. Chance Constrained Optimization for Wind Power Curve Fitting with Unclean Data;2024 IEEE Congress on Evolutionary Computation (CEC);2024-06-30