Human Segmentation Based on Compressed Deep Convolutional Neural Network

Human Segmentation Based on Compressed Deep Convolutional Neural Network

Most semantic segmentation models based on deep convolutional neural network (CNN) typically require a large number of weight parameters, high hardware resources for storage and computation. Moreover, redesigning a compact network suffers from some training problems, such as under-fitting. A human s...

Full description

Bibliographic Details
Main Authors: Jun Miao, Keqiang Sun, Xuan Liao, Lu Leng, Jun Chu
Format: Article
Language:English
Published: IEEE 2020-01-01
Series:IEEE Access
Subjects:
Compressed deep convolutional neural network
human segmentation
convolutional-layer level pruning
filter level pruning
Online Access:https://ieeexplore.ieee.org/document/9195490/

Internet

https://ieeexplore.ieee.org/document/9195490/

Similar Items