Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

Convolutional Factor Analysis Inspired Compressvie Sensing

Abstract: 

We solve the compressive sensing problem via convolutional factor analysis, where the convolutional dictionaries are learned in situ from the compressed measurements. An alternating direction method of multipliers (ADMM) paradigm for compressive sensing inversion based on convolutional factor analysis is developed. The proposed algorithm provides reconstructed images as well as features, which can be directly used for recognition (e:g:, classification) tasks. We demonstrate that using  30% (relative to pixel numbers) compressed measurements, the proposed model achieves the classification accuracy comparable to the original data on MNIST.

up
0 users have voted:

Paper Details

Authors:
Yunchen Pu
Submitted On:
17 September 2017 - 11:10am
Short Link:
Type:
Presentation Slides
Event:
Presenter's Name:
Xin Yuan
Paper Code:
MQ-L2.1
Document Year:
2017
Cite

Document Files

Slides_ICIP_2017.pdf

(179 downloads)

Keywords

Additional Categories

Subscribe

[1] Yunchen Pu, "Convolutional Factor Analysis Inspired Compressvie Sensing", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2216. Accessed: Sep. 24, 2018.
@article{2216-17,
url = {http://sigport.org/2216},
author = {Yunchen Pu },
publisher = {IEEE SigPort},
title = {Convolutional Factor Analysis Inspired Compressvie Sensing},
year = {2017} }
TY - EJOUR
T1 - Convolutional Factor Analysis Inspired Compressvie Sensing
AU - Yunchen Pu
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2216
ER -
Yunchen Pu. (2017). Convolutional Factor Analysis Inspired Compressvie Sensing. IEEE SigPort. http://sigport.org/2216
Yunchen Pu, 2017. Convolutional Factor Analysis Inspired Compressvie Sensing. Available at: http://sigport.org/2216.
Yunchen Pu. (2017). "Convolutional Factor Analysis Inspired Compressvie Sensing." Web.
1. Yunchen Pu. Convolutional Factor Analysis Inspired Compressvie Sensing [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2216