A Deep Convolutional Neural Network with Selection Units for Super-Resolution
Citations Over TimeTop 10% of 2017 papers
Abstract
Rectified linear units (ReLU) are known to be effective in many deep learning methods. Inspired by linear-mapping technique used in other super-resolution (SR) methods, we reinterpret ReLU into point-wise multiplication of an identity mapping and a switch, and finally present a novel nonlinear unit, called a selection unit (SU). While conventional ReLU has no direct control through which data is passed, the proposed SU optimizes this on-off switching control, and is therefore capable of better handling nonlinearity functionality than ReLU in a more flexible way. Our proposed deep network with SUs, called SelNet, was top-5 th ranked in NTIRE2017 Challenge, which has a much lower computation complexity compared to the top-4 entries. Further experiment results show that our proposed SelNet outperforms our baseline only with ReLU (without SUs), and other state-of-the-art deep-learning-based SR methods.
Related Papers
- → Deep fake Detection Through Deep Learning(2023)4 cited
- Simultaneous multiplication of multiple numbers(2015)
- → Multiplication is repeated addition(1965)3 cited
- → Productive Pieces: Exploring Multiplication on the Overhead(1982)
- Methods of multiplication(2015)