MrChenFeng/SSR_BMVC2022
SSR: An Efficient and Robust Framework for Learning with Unknown Label Noise (BMVC2022)
This framework helps machine learning practitioners build more accurate image classification models even when their training data has incorrect labels. It takes a dataset of images with potentially noisy labels and produces a more robust classification model. Data scientists and machine learning engineers who work with real-world image datasets that are difficult to curate perfectly would use this.
No commits in the last 6 months.
Use this if you need to train a reliable image classification model but know your image dataset contains some incorrectly assigned labels that are hard to fix manually.
Not ideal if your primary concern is training time or if you have a perfectly clean, accurately labeled dataset.
Stars
31
Forks
7
Language
Python
License
MIT
Category
Last pushed
Mar 22, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/MrChenFeng/SSR_BMVC2022"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
AdaptiveMotorControlLab/CEBRA
Learnable latent embeddings for joint behavioral and neural analysis - Official implementation of CEBRA
theolepage/sslsv
Toolkit for training and evaluating Self-Supervised Learning (SSL) frameworks for Speaker...
PaddlePaddle/PASSL
PASSL包含 SimCLR，MoCo v1/v2，BYOL，CLIP，PixPro，simsiam, SwAV, BEiT，MAE 等图像自监督算法以及 Vision...
YGZWQZD/LAMDA-SSL
30 Semi-Supervised Learning Algorithms
ModSSC/ModSSC
ModSSC: A Modular Framework for Semi Supervised Classification