icgy96 / apr Goto Github PK
View Code? Open in Web Editor NEW[ICCV 2021] Amplitude-Phase Recombination: Rethinking Robustness of Convolutional Neural Networks in Frequency Domain
Home Page: https://arxiv.org/abs/2108.08487
License: MIT License
[ICCV 2021] Amplitude-Phase Recombination: Rethinking Robustness of Convolutional Neural Networks in Frequency Domain
Home Page: https://arxiv.org/abs/2108.08487
License: MIT License
Hi
I see that in both APR-P and APR-S there is some randomness in the augmentations. For APR-P, the data is mixed only 40% of the time
Line 16 in ca61e35
and in APR-S, the data is augmented 50% of the time
Line 25 in ca61e35
with additional randomness in the choice of image whose phase is returned
Line 46 in ca61e35
Were these steps used to obtain the results in your paper, as I do not find this randomness mentioned in the paper?
Also, could you briefly describe how APR-SP was implemented - did you first apply APR-S and then apply APR-P?
Thank you,
KC
I want to use your pretrain model to do other experiments.
Can you share your ResNet-50 model checkpoint?
Thanks
I read your paper very impressive using Fourier transform.
I wish I could have the implementations to run the AutoAttack experiments.
Can you share your code for FSGM training/eval?
Hi @iCGY96! Thanks for your insightful work! I found it is hard to understand in Section 5.3: Labeled by Amplitude or Phase? In this section, the authors investigated the use of labels amplitude and phase separately. "The model is trained for the sample x combined by the phase spectrum Pxi and the amplitude spectrum Axj by optimizing Eq(7)". How to understand x combined by the phase spectrum P and the amplitude spectrum A. Is it means that you first decouple the x into A and P, then input the A and P to the networks with two FC
layers, or input [X, P] and [X, A] into the networks?
if you have tried ./main.py and prepared datasets in ./data, and you want to train the code in ./autoattacks like me, attention here.
in line 26 of train_fgsm.py:
parser.add_argument('--data-dir', default='../data', type=str)
should be modifieed to:
parser.add_argument('--data-dir', default='../data/cifar10', type=str)
the shared link of APR-SP model seems broken, and yields a 404 error
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.