Comments (4)
Hi,
The lower EER the better. On CelebA_Spoof Aenet has better results. It has more parameters and better fits the data. But on cross-domain performance (LCC_FASD), the MN3 has better descriptive ability based on metrics. At the same time MN3 noticeably faster in real-time performance.
from light-weight-face-anti-spoofing.
Yeah MN3 is much faster, I noticed that too. Yet, since antispoofing is a very challenging task with only rgb frame, even AENET isn't very stable, but it is the most accurate one I came accross so far. It's speed is enough for me as well.
Also CelebA_Spoof dataset is the best one I have seen so far, I even found your project while searching CELEBA_Spoof, so AENET being good only on their own dataset isn't the worst thing.
Or do you think LCC_FASD is better and more general, thus MN3 trained with LCC_FASD is a better solution?
from light-weight-face-anti-spoofing.
I agree CelebA_Spoof dataset is the best one for now. MN3 is trained on it and LCC_FASD is used for testing purposes. This is a good option since CelebA has more quality images. From professional camera and magazine covers. LCC_FASD has different images taken from poor quality webcams and smartphones, it's more challenging for testing. When I developed the training pipeline I came across a cross-domain problem. The better model fit the CelebA the worse results were on LCC_FASD. Applying some techniques I managed to receive almost the same metrics on CelebA as the AENET did, but It turns out that generalization dropped a lot. So, I had to choose the golden middle sacrificing metric on the CelebA.
Overall, it's a really challenging task, both of the models perform not so stable in real life and there is room for growth and improvement.
from light-weight-face-anti-spoofing.
Yeah I agree, its one of the most challenging tasks in ML and also unfortunately not a very popular one.
About being stable, both aenet and mn3 depend heavily on the quality of camera and lighting conditions. After trial and errors, I came to the conclusion they work the best with FHD camera (with high NIR efficiency) and external NIR lighting. Only challenge I faced is, network mistakes surgical masked face as fake.
from light-weight-face-anti-spoofing.
Related Issues (20)
- how to solve this problem? HOT 1
- how to use LCC_FASD dataset without cropping?
- openvino version
- No such file or directory: './logs/MobileNet3.pth.tar'
- When I run the code, I have a problem like this, can you help me?
- casia cefa train test labels HOT 1
- How to use resnet50 or other models to train the dataset? Thank you. HOT 2
- Running inference of trained model
- Model Classifies all brown or dark people as spoof HOT 1
- Can't run bash init_venv.sh HOT 1
- The confidence score HOT 1
- AttributeError: 'openvino.inference_engine.ie_api.IECore' object has no attribute 'read_network'
- Image normalisation while predicting in demo.py HOT 1
- Low accuracy on lcc-fasd
- Convert pytorch module to openvino HOT 1
- image net weights HOT 1
- problem with face detector HOT 1
- hello i am getting error below HOT 1
- transfer learning step?
- How to use MN3_antispoof.pth.tar
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 light-weight-face-anti-spoofing.