elijahcole/single-positive-multi-label
Multi-Label Learning from Single Positive Labels - CVPR 2021
This project helps computer vision researchers and practitioners automatically assign multiple descriptive labels to an image when only a single correct label is known during training. You provide image datasets with partial labels, and it outputs a model capable of predicting all relevant labels for new images. It's designed for those working with large image collections where exhaustive labeling is too costly.
No commits in the last 6 months.
Use this if you need to train a robust image classifier for multiple attributes or objects, but your training data only has one or a few positive labels specified per image, rather than all of them.
Not ideal if your image datasets are fully labeled with all relevant attributes for training, as this method specifically addresses incomplete label information.
Stars
97
Forks
23
Language
Python
License
MIT
Category
Last pushed
Nov 21, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/elijahcole/single-positive-multi-label"
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