ElasticFace
Official repository for ElasticFace: Elastic Margin Loss for Deep Face Recognition (by fdbtrs)
| ElasticFace | FairScoreNormalization | |
|---|---|---|
| 1 | 1 | |
| 152 | 4 | |
| - | - | |
| 0.0 | 10.0 | |
| about 1 year ago | over 3 years ago | |
| Python | Python | |
| - | - |
The number of mentions indicates the total number of mentions that we've tracked plus the number of user suggested alternatives.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
ElasticFace
Posts with mentions or reviews of ElasticFace.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2023-05-26.
-
Face recognition models require different thresholds for different races? [D]
Hey, first of all, don't use FaceNet. It is outdated and performs way worse than modern solutions. You can use Elastic Face or MagFace (or any other SOTA FR model).
FairScoreNormalization
Posts with mentions or reviews of FairScoreNormalization.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2023-05-26.
-
Face recognition models require different thresholds for different races? [D]
And yes, there are performance differences between ethnicities. You can either calculate a global decision threshold for all subgroups in your dataset for a given and fixed FMR, or you can apply normalization techniques. You could apply Group Based Score Normalization to calculate different thresholds for your subgroups and then use these in the normalisation procedure when doing the comparison. But when applying these techniques you should check the FNMR at different FMRs.
What are some alternatives?
When comparing ElasticFace and FairScoreNormalization you can also consider the following projects:
pytorch-learn-reinforcement-learning - A collection of various RL algorithms like policy gradients, DQN and PPO. The goal of this repo will be to make it a go-to resource for learning about RL. How to visualize, debug and solve RL problems. I've additionally included playground.py for learning more about OpenAI gym, etc.
StyleGAN.pytorch - A PyTorch implementation for StyleGAN with full features.
ALAE - [CVPR2020] Adversarial Latent Autoencoders
manga-image-translator - Translate manga/image 一键翻译各类图片内文字 https://cotrans.touhou.ai/