BoyuanChen/label_representations
[ICLR 2021] Beyond Categorical Label Representations for Image Classification
When training image classification models, this project explores using rich, high-dimensional labels instead of simple categories. It takes image datasets and different label types (like speech or composite images) to train classification models. This tool is for researchers and practitioners in machine learning and computer vision who are experimenting with novel ways to improve model robustness and data efficiency.
No commits in the last 6 months.
Use this if you are a machine learning researcher interested in exploring how different label representations, beyond basic categories, can impact image classification performance, especially with limited data or when facing adversarial attacks.
Not ideal if you are looking for a pre-built, production-ready image classification system or if your primary goal is to apply standard categorical classification without exploring novel label representations.
Stars
25
Forks
8
Language
Python
License
MIT
Category
Last pushed
Dec 12, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/BoyuanChen/label_representations"
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