Comments (5)
Task id is not required, but we need to know whether the test instance belongs to the last-learned task or not (note that this is a much weaker requirement when compared to task aware methods). We have explained this in Sec 3.2.2. We can side-step this by learning a simple binary classifier to do the discrimination.
from eli.
thank you! and could you tell me the position of the code for it?
btw, did the binary classifier not suffer from the class imbalance problem (rehearsal data vs. new data) in experiments?
from eli.
Hi, I think you got me wrongly. ELI doesn't have the binary classifier, but that can be one way to get around the weak requirement that we have. We will explore this in a future work.
from eli.
the current results are obtained with information (belongs to the last-learned task or not) of test data?
from eli.
Yes.
from eli.
Related Issues (8)
- How to obtain the test results? HOT 14
- code url of OW-DETR is wrong HOT 2
- The version of software HOT 1
- question about aligning during inference HOT 3
- How to reproduce the results in the paper? HOT 2
- How can I get "./base_50.pt"? HOT 4
- Do you selecet 'difficult'=0 and 'difficult'=1 samples for each category, when spliting VOC datasets?
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 eli.