Comments (3)
Hi, thanks for your question.
Basically, the magnitude of perturbation in LVAT (1.0-1.5) is smaller than that of VAT (2.5-8.0).
These are empirical results but are also able to be explained theoretically.
Space where the perturbation is added in LVAT is the latent space, N(0,I).
The latent space is very packed compared to the input image space because all of the images in the (training) dataset will be contained in the region of N(0,I).
Thus, the perturbation magnitude = 1.0 is sufficiently large in the latent space.
Actually, it is the hardest point all the time I have explained LVAT to someone, and thus if it's still unclear please ask again.
from lvat.
Thank you for your answer!!
from lvat.
Thank you for your answer!!
from lvat.
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 lvat.