Comments (3)
Thank you for your interest in our survey.
We think the goal of these three papers can be considered as establishing a task or dataset map similar to Taskonomy [1], which typically does not consider specific target datasets but instead builds a similarity map within an existing model zoo or dataset zoo.
The "model transferability estimation" task in our survey focuses on the issue of proposing a metric for a given target dataset, which is a relatively smaller problem, hence these papers were not included at this time.
We briefly described the difference in the section on task transferability in related work, sorry for not explaining it clearly, and we will further improve the paper.
In fact, we also considered a more comprehensive survey to include these articles initially, but due to conference page limits, we only included papers related to this smaller issue. A comprehensive survey is our future work.
[1] Taskonomy: Disentangling task transfer learning
from awesome-model-transferability-estimation.
I noticed that you have closed the issue, hoping your concerns have been addressed.
If you have any further questions, feel free to contact me.
from awesome-model-transferability-estimation.
Thanks for the detail reply. I see the differences between the three papers we discussed and your survey so I close the issue after I created. I also noticed the inclusion of another gradient attribution method paper in your references, which addresses my concerns. Appreciate for your effort and responds. Thanks again
from awesome-model-transferability-estimation.
Related Issues (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 awesome-model-transferability-estimation.