EIDOSLAB/unbiased-contrastive-learning
Code for the paper "Unbiased Supervised Contrastive Learning" | ICLR 2023 https://openreview.net/forum?id=Ph5cJSfD2XN
When training image recognition models, they can often learn shortcuts from 'biased' datasets, performing well on specific training examples but failing on real-world images. This project helps researchers and machine learning engineers create more robust AI models by providing techniques to train them to focus on true features rather than dataset-specific quirks. It takes in biased image datasets and outputs more reliable and accurate image classification models.
No commits in the last 6 months.
Use this if you are a machine learning researcher or practitioner struggling with model performance degradation on real-world data due to biases in your training datasets.
Not ideal if you are looking for a plug-and-play solution for general data cleaning or a non-vision-based machine learning task.
Stars
13
Forks
1
Language
Python
License
MIT
Category
Last pushed
Sep 22, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/EIDOSLAB/unbiased-contrastive-learning"
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