wy1iu/LargeMargin_Softmax_Loss

Implementation for in ICML'16.

50
/ 100
Established

This project offers a specialized loss function for training neural networks to achieve more distinct and separable classification boundaries. It takes raw data inputs (like images or sensor readings) and helps produce clearer categorization and more reliable feature representations for tasks like facial recognition. It's designed for machine learning engineers and researchers aiming to improve the robustness of their classification models.

352 stars. No commits in the last 6 months.

Use this if you are training convolutional neural networks for classification or feature embedding and need to improve the model's ability to distinguish between very similar categories, especially in biometrics.

Not ideal if you are looking for a plug-and-play solution for general data analysis, as this requires integration into a neural network training pipeline.

biometric-verification image-classification feature-learning face-recognition machine-learning-engineering
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 24 / 25

How are scores calculated?

Stars

352

Forks

112

Language

C++

License

Last pushed

Aug 27, 2018

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/wy1iu/LargeMargin_Softmax_Loss"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.