Comments (2)
Hi @PeikeLi ,
you are right, images with unseen classes are not used.
The unseen gt labels are used in order to infer the statistics of appearance of each unseen classes.
Maxime
from zs3.
from zs3.
Related Issues (14)
- The use of unseen labels during the training! HOT 3
- Using unseen classes GT labels make no sense for zero-shot setting HOT 3
- Missing Final deeplabv3+ and GMMN with graph context weights in the case of 2 unseen classes
- How can I reproduce the results for the baseline model described in experiments section?
- I think the classes-59 is from https://github.com/shelhamer/fcn.berkeleyvision.org/tree/master/data/pascal-context . Is that right?
- SBD dataset HOT 1
- Try out on own example?
- Dimension of output tensors in eval_pascal.py not match HOT 1
- You cannot use unseen label info in the training process HOT 2
- Reproduction issue HOT 1
- the usage of unseen class segmentation annotations HOT 2
- Pascal context splits
- How to generate norm_embed_arr_300.pkl? HOT 1
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 zs3.