Comments (5)
You are correct from the computation perspective. But the result of DCT is more interpretable since different frequency components are separated. While the result of convolution is less interpretable since different frequency components are mixed.
from dctnet.
You are correct from the computation perspective. But the result of DCT is more interpretable since different frequency components are separated. While the result of convolution is less interpretable since different frequency components are mixed.
Interpretable is not a objective word. Especially for the first level of CNN. Many papers have interpret the function of low level convolution.
DCT is definitely a certain form of convolution. DCT = ONLY ONE LAYER CONVOLUTION. This paper just use another way to explain convolution, because DCT are just kernels with orthogonality. The conclusion will mislead readers. This kind of decoration and lacking depth discussion will become a bluff in DL research.
If this paper could deeply discuss the effectiveness of manual designed low level kernels (Such as DCT, Haar-like, HOG, LBP...) with different parameters, it will be valuable.
from dctnet.
from dctnet.
You are correct that DCT is definitely a certain form of convolution. But our paper is not aiming to use another way to explain convolution. Instead, we explore the importance of each frequency component in several tasks. DCT is just a tool to transform data to the frequency domain. So please point out which conclusion is misleading readers, then we can discuss further. Thanks.
explore the importance of each frequency component is more accurate than Learning in the Frequency Domain. But still needs further discussion.
from dctnet.
Thanks for your suggestion.
from dctnet.
Related Issues (20)
- look for "block_composition" HOT 10
- Do you transform the images from BGR to YCbCr color space? HOT 2
- pretrained model can't be downloaded HOT 1
- The mobilenetv2 cannot be evaluated with your pretrained models. HOT 1
- the link to Training code is not available now ,could you update it again? HOT 5
- Cifar model not found
- About mean and std in transfrom HOT 2
- pretrained model can't be downloaded HOT 1
- How do you group the components with same frequency into one channel? HOT 1
- The code is so bad HOT 2
- pretrained model can't open HOT 5
- Questions about the dataloader and missing files HOT 1
- Missing transforms (ToYCrCb, ChromaSubsample, UpsampleDCT, CenterCropDCT) in cvtransforms.py HOT 3
- update training code
- how to decompress the pretrained model?
- could you share the env config?
- ModuleNotFoundError: No module named '_dctfromjpg_wrapper'
- RuntimeError: Wrong JPEG library version: library is 62, caller expects 90 solved
- 数据预处理
- 2✖ upsampling
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from dctnet.