Personal tools

Difference between revisions of "Learning Image Decompression with Convolutional Networks"

From iis-projects

Jump to: navigation, search
(Created page with "<!--400px|thumb --> 200px|thumb ==Description== Convolutional Neural Networks (ConvNets) have shown break-thro...")
 
Line 10: Line 10:
 
: Looking for 1 Master or (1 or 2) semester project students (work load will be adjusted)  
 
: Looking for 1 Master or (1 or 2) semester project students (work load will be adjusted)  
 
: Contact/Supervision: [[:User:Lukasc | Lukas Cavigelli]]
 
: Contact/Supervision: [[:User:Lukasc | Lukas Cavigelli]]
[[Category:Hot]] [[Category:Digital]] [[Category:System Design]] [[Category:Available]] [[Category:Semester Thesis]] [[Category:Master Thesis]] [[Category:Lukasc]]
+
[[Category:Hot]] [[Category:Digital]] [[Category:System Design]] [[Category:Available]] [[Category:Semester Thesis]] [[Category:Master Thesis]] [[Category:Lukasc]] [[Category:Software]]
 
<!--  
 
<!--  
 
===Status: {Available, Reserved, In Progress, Completed}===
 
===Status: {Available, Reserved, In Progress, Completed}===

Revision as of 15:55, 24 February 2016

Image-compression.jpg

Description

Convolutional Neural Networks (ConvNets) have shown break-through performance and/or performance-per-power on many computer vision tasks such as classification, image segmentation, optical flow and super-resolution. We think that applying ConvNets for the compression of image data could be a promising approach. For this we would have to think about how we can limit the information capacity of the output signal, e.g. through quantization. A nice aspect of this application is that the usually limited training data is not an issue, since randomly acquired images our the internet can be used to train the network.

In this project you learn the basics of ConvNets, develop such a quantization module, explore cost functions to be minimized and ConvNet architectures suitable for this purpose, and evaluate the results against existing compression schemes such as JPEG 2000.

Status: Available

Looking for 1 Master or (1 or 2) semester project students (work load will be adjusted)
Contact/Supervision: Lukas Cavigelli

Prerequisites

Decent Matlab and C programming skills
Motivation for signal processing problems
Ideally some knowledge of GPU programming

Character

20%-30% Theory
20%-30% C/CUDA programming
50% ConvNet model design (Lua/Torch coding) and evaluation (Matlab)

Professor

Luca Benini

↑ top