Comments (4)
Hi yutao,
Thanks for sharing your inspiring work. I have a question about the specific implementation of Region Norm. As you've mentioned in your paper, Region Norm should be a generation to Instance Norm. However, from your implementation, rn is still based on the distribution of mask/unmask regions in the whole batch. Is there some errors in your implementation, or you've found that performance based on instance regions worse than batch regions.
Hi, thanks for your comments. It's exactly what we are going to make a statement in the future application of RN.
First, sorry that we didn't discuss this in the AAAI2020 paper. RN wants to bring an insight that spatially region-wise normalization is better for some CV tasks such as inpainting. Theoretically, RN can be both BN-style or IN-style. Both have pros and cons. IN-style RN gives less blurring results and achieves style consistence to background in some extent, while suffers from spatial inconsistence if the model representation ability is limited. BN-style RN gives higher PSNR on an aligned validation data, but makes regions more blurring and causes much data-bias risk when testing data distribution has a certain shift to training data distribution. One chooses the RN style according to the specific scene.
Thanks.
from rn.
from rn.
the generated region is not well blended in background regions.
- " the generated region is not well blended in background regions": I think there are many possible reasons such as data distribution shift. You can also re-train RN on ImageNet. Maybe the results be better.
- I didn't try removing the gamma. But pls share the results on it to me if you gonna do it.
Feel free to ask me if you still have questions.
Best
from rn.
Look forward to future discussing.
Best
from rn.
Related Issues (20)
- Why use the given pre-training model to get such results? HOT 2
- Training on custom dataset with custom mask for Inpainting HOT 1
- the loss is None HOT 1
- I have trained this on single gpu with cuda 11.2 and pytorch 1.8 but still confuse about multi-gpu training HOT 1
- wu
- 无结果
- i wana better result plz help HOT 10
- bad results HOT 14
- Details for training Places2 dataset and irregular mask HOT 4
- About loss function HOT 1
- Questions about training
- About your pretrained model HOT 1
- Please provide demo images to run your test. HOT 1
- How to test it for a single photo. HOT 1
- Example Inputs and masks for evaluation HOT 3
- Question about more regions (K>2) HOT 1
- add one more channel HOT 1
- 请问一下训练后的结果在哪里测试呢?没看见有测试程序啊 HOT 1
- 关于修复结果的请教 HOT 5
- About output from the pretrained model
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 rn.