Comments (6)
What do you mean by accuracy is reduced (the accuracy is lower compared to what)? Do you mean the accuracy of [trained pointnet on defended point cloud] is lower than [original pointnet on clean point cloud]? This is somewhat expected, because defense methods will inevitable distort point clouds a bit, thus degrading the performance. I guess as long as the degradation is not a lot (say, 2%), it is acceptable.
from if-defense.
Yes, we use the defense method on mn40_random2048.npz to obtain **def_mn40.npz** for hybrid training of pointnet, and then test pointnet against the attack-free point cloud data def_attack_data.npz after defense processing. Compared with the normally trained pointnet, the accuracy of the hybrid trained pointnet dropped by about 10%. This problem bothers me.
from if-defense.
Hum, that's a lot. Did you only train on def_attack_data.npz
, or did you train on a mix of def_attack_data.npz
and mn40_random2048.npz
? In my paper, I did mixed training, so that the model performance is high on both defended and clean point cloud.
Mix training is just when training the model, we randomly sample data from both sets in a batch.
from if-defense.
I trained on a mix of def_attack_data.npz
and mn40_random2048.npz
, but the model only performs well on clean data.
from if-defense.
That's very weird. In my case I trained on both data, and it works well on both clean data and defended data (still slight drop in performance, but not a lot). Maybe your defended data are too different from the clean data, so there is domain gap, which makes the model hard to perform well in both cases. I suggest you check your defense method for this.
from if-defense.
Well, thank you for your patience in answering.
from if-defense.
Related Issues (14)
- Why the attack acc of attack_script and inference.py is different? HOT 4
- Could you please provide more details about training conv-o-net on modelnet40? HOT 5
- Could you send me the attack results of LG-GAN and AdvPC ? HOT 2
- Question about perturb attack on pointnet++ HOT 1
- Target label choosing stragegies HOT 2
- Question about the adaptive attack ? HOT 3
- the location of /pretrain folder HOT 2
- Save the generated attack images HOT 1
- Is there a training code for DUP-Net? HOT 1
- How to perform defense HOT 3
- Production of data sets HOT 1
- Hybrid training data HOT 4
- How to train ConvONet on other datasets? HOT 3
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 if-defense.