Comments (9)
Hi,
Thank you for being interested in our work.
The preprocessed ground truth images of CANet are actually processed by the scripts of OSLSM and therefore the small objects are also removed in the project of CANet (we have confirmed with the authors of CANet before we submit our paper).
Also, I think it is okay to follow OSLSM to screen out small objects (we only remove them for support samples) because OSLSM is the first paper that proposes the setting of few-shot segmentation.
Frankly speaking, it is hard to keep all papers to have the same configuration. If you want to have a comparison, you can try to remove the small objects for support samples using the repo of PANet or keep them in our repo to see the performance gap it causes to the model.
Thank you and hope my explanation is helpful.
from pfenet.
I think it is more practical to only remove them for support samples. Thanks for your explanation!
from pfenet.
Sorry to bother you again. But do you mean OSLSM and CANet remove small objects in both support and query set?
from pfenet.
@LiheYoung I think the small objects are removed in CANet. However, from my perspective, we do not want to alter the data sample for validation (query samples), even if some objects are small and hard for models to identify, therefore we only remove them from support samples.
from pfenet.
@tianzhuotao Thanks for your explanation!
from pfenet.
I take a closer look at the dataloading process.
It seems that if an image doesn't contain any objects from current class space (such as base/novel class) larger than 2x32x32, the image will be removed from the data list. This image will never be selected during current phase. And the small query objects in these removed images will never be sampled. Therefore, actually, it still removes a portion of small query objects, which may bring slight better performance.
Is there anything I misunderstand? Thanks!
from pfenet.
Thank you for mentioning it!
I overlooked this point when I reviewed my code. Yes, a portion of small objects in the query set has been excluded in my implementation, which causes very little improvement on average in my case. But it still has an overall fair comparison with other methods I think.
However, this repo can achieve higher performance than the results reported in my original paper (see this issue). Of course, for a fair comparison, you can accordingly modify my code to be the same as that in your setting.
Thank you again! Please drop me a message if you have further questions.
from pfenet.
@tianzhuotao Thanks for your reply!
from pfenet.
Why my test result of moiu is 0
from pfenet.
Related Issues (20)
- Questions about PFENet++ HOT 1
- Training Details HOT 1
- FFENet++ source code HOT 1
- 5-shot resnet50 parameters HOT 2
- Questions about the backbone HOT 2
- Problem in code HOT 3
- Dataset replacement HOT 1
- 数据集中的训练集和测试集 HOT 1
- How to run demo on windows HOT 1
- Episode setting HOT 1
- training detailing HOT 1
- implement detail about PFENet HOT 1
- About the SBD dataset HOT 4
- About the Pascal 5i HOT 1
- resnet50 COCO weigths HOT 1
- about BN HOT 1
- About "train_loader" and "val_loader" in train.py HOT 1
- train on my data HOT 2
- weights
- 预训练模型不能下载 HOT 2
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 pfenet.