Comments (4)
Hi, @pengsongyou. I know the key in this paper is to construct a CLIP latent feature supervised 3D semantic backbone which has better generalization ability.
But I just wanted to clarify that the distillation training approach you are using is not a strict zero-shot segmentation setting. During distillation training, all points or pixels are used to train the 3D backbone regardless of whether they are seen or unseen categories. However, during zero-shot testing, you split the categories into seen and unseen, and only the unseen categories are used for evaluation.
In my opinion, in a zero-shot setting, the unseen points or pixels should not be used at all during training, regardless of the training strategy used.
regards,
zihui
from openscene.
Hi @ZhengLeon ,
During distillation, the only loss we have is the cosine similarity loss between the 2D fused features and the predicted per-point features. We do not really classify seen/unseen objects since we do not consider the object classes/labels at all. Please refer to section 3.2 in our paper.
Best
Songyou
from openscene.
Hi, @pengsongyou. I know the key in this paper is to construct a CLIP latent feature supervised 3D semantic backbone which has better generalization ability. But I just wanted to clarify that the distillation training approach you are using is not a strict zero-shot segmentation setting. During distillation training, all points or pixels are used to train the 3D backbone regardless of whether they are seen or unseen categories. However, during zero-shot testing, you split the categories into seen and unseen, and only the unseen categories are used for evaluation.
In my opinion, in a zero-shot setting, the unseen points or pixels should not be used at all during training, regardless of the training strategy used.
regards, zihui
Well, I think this is a good challenge. As it was discussed in "Definition of Zero-Shot Learning (ZSL)", supplementary, Sec. B. The ZSL setting followed in this paper is not quite strict. In real-world applications, however, train and inference on customized data without labeling can help a lot. Manpower consumption is more concerned.
from openscene.
Yes, as @argosdh pointed out, we discussed this in the supplementary material. You can check it out. Basically, we follow the ZSL definition from the original CLIP paper, and many of its follow-up papers (e.g. LSeg, OpenSeg, etc), which is not strictly the same as the classic ZSL definition. Hope it clarifies your concern.
And sorry I missed your comments earlier and only replied now.
from openscene.
Related Issues (20)
- Feature fusion of nuScenes HOT 2
- Matterport Evaluation Error HOT 2
- Working with Frame parameters for Replica feature fusion HOT 4
- train on my own dataset HOT 1
- How to get the ".pt" file๏ผ HOT 1
- Multi-view fusion in nuscenes HOT 1
- How to get 'scene.ply' in nuScenes HOT 8
- Nuscenes validate set HOT 1
- Training Time HOT 1
- Inference speed on the nuScenes Lidarseg HOT 1
- Evaluation with "model.eval()" HOT 3
- "Unable to connection" error when running the demo HOT 1
- Failed to clone demo/gaps HOT 1
- Multiview fusion in nuScenes HOT 7
- Openseg feature HOT 1
- Could you share nuscenes_3d/train data ? HOT 2
- About the LSeg
- About LSeg feature HOT 1
- LSeg Feature and Evaluate HOT 2
- LSeg on ScanNet HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
๐ 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. ๐๐๐
-
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 โค๏ธ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from openscene.