Comments (4)
Thanks for your interest in our dataset. The main reason for doing the data augmentation is to increase the number of points for the underrepresented semantic classes and to improve the semantic segmentation performance. The selected classes were having a low semantic segmentation performance during our experiments. The ground was included because all objects are connected to it, and the semantic segmentation needs to split it with the other objects.
from stpls3d.
Thanks for your reply. I understand the purpose of the data augmentation. The weighted loss also alleviates the data unbalance problem. However, I am confused about such data augmentation implementation. In my understanding, you apply data augmentation to the whole point cloud, and then only keep points belonging to these classes [0, 2, 3, 7, 8, 9, 12, 13] and filtered out all other points. However, such augmented training samples represent 'incomplete scenes', right? I think a more reasonable way would be to apply the data augmentation to these classes [0, 2, 3, 7, 8, 9, 12, 13] and keep other points unchanged instead of filtering out them.
from stpls3d.
Yes, I totally agree with you that the augmented training samples represent 'incomplete scenes', and this may cause problems. This was my concern as well before, but the experiment showed "reasonable" results from this augmentation (increased performance in these underrepresented classes). One of the purposes is to increase the #of points / % of points for these underrepresented classes and adding other points back may still make these classes underrepresented.
In addition, if you check the classes that were removed, you can see that buildings (1) and high vegetation (4) have too many points, and adding them back will make the training process take too long.
Another interesting thing about this is, by using the augmented 'incomplete scenes', it basically removed some of the contextual relationships between objects (if there were any). And does contextual relationships between objects actually maters is still a good research topic I think. From the recent work of "Mix3D: Out-of-Context Data Augmentation for 3D Scenes", it seems like Context may not matter that much in the 3D scene segmentation, especially in the outdoor environments with a limited sample size that can feed to a network. This is just my opinion and I could be totally wrong since this was only tested with HAIS and PointGroup which are voxelization-based networks. I'm not sure if it will work for other types of networks such as KpConv or RandLA (point-based) since they behave differently (though Mix3D worked with KpConv).
from stpls3d.
Interesting and insightful explanation! Thanks :)
from stpls3d.
Related Issues (20)
- HAIS one point assigned to multiple instance proposals HOT 4
- about OA_from_confusions in kpconv HOT 1
- How to use the evaluation script for the competition of instance segmentation?
- How to inference in the test set of stpls3d dataset? HOT 2
- mAP (Intersection) calculation in the evaluation script HOT 3
- instance label 0 mean HOT 13
- I want to make my own dataset HOT 6
- Scores in the evaluation script HOT 4
- training with randla HOT 11
- Pre-trained models and dataset generation HOT 6
- Can I use the synthetic data generation pipeline to create my dataset? HOT 1
- Data format of STPLS3D txt point clouds for Instance Segmentation HOT 1
- Error while set up the environment for Instance Segmentation in Ubuntu 20.04 HOT 2
- Interested in the projection code HOT 2
- KPConv-STPLS3D- Data Problem HOT 2
- multi gpu HOT 2
- Download failed in Google Drive HOT 1
- A Problem about HAIS Model in Stpls3d Dataset
- About Randla
- Overfitting was observed in the Synthetic v3 region
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 stpls3d.