Difference between revisions of "Learning Image Decompression with Convolutional Networks"
From iis-projects
m |
|||
Line 7: | Line 7: | ||
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. | 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: | + | ===Status: In Progress=== |
+ | Thilo Weber, Jonas Wiesendanger | ||
: 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: | + | [[Category:Hot]] [[Category:Digital]] [[Category:System Design]] [[Category:In progress]] [[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 22:51, 13 March 2016
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: In Progress
Thilo Weber, Jonas Wiesendanger
- 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)