zhangchbin/OnlineLabelSmoothing

The official code for the paper "Delving Deep into Label Smoothing", IEEE TIP 2021

40
/ 100
Emerging

This project helps machine learning practitioners improve the accuracy of image classification models, especially for fine-grained categories like specific car models or bird species. By applying an "online label smoothing" technique during model training, it takes labeled image datasets and outputs a more robust and accurate classification model. This is for researchers or engineers who are building and training deep learning models for image recognition tasks.

No commits in the last 6 months.

Use this if you are working on image classification problems where distinguishing between very similar categories is crucial, such as in biology, manufacturing quality control, or specialized object recognition.

Not ideal if you are looking for a pre-trained, ready-to-use model for general image classification without needing to delve into the training process.

image-classification fine-grained-recognition deep-learning-training computer-vision model-robustness
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

81

Forks

12

Language

Python

License

MIT

Last pushed

Jul 06, 2022

Commits (30d)

0

Get this data via API

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

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