Correr-Zhou/SPML-AckTheUnknown
[ECCV 2022] Offical implementation of the paper "Acknowledging the Unknown for Multi-label Learning with Single Positive Labels".
This project helps researchers and machine learning practitioners build more accurate image classification models when their training data has incomplete labels. It takes image datasets where only some object categories in each image are positively identified, and produces a trained model that can more reliably identify all objects present. This is designed for those working with large image collections where manually labeling every single object is impractical.
No commits in the last 6 months.
Use this if you are performing multi-label image classification and only have single positive labels per image, but need the model to predict all relevant labels accurately.
Not ideal if your dataset has exhaustive multi-label annotations or if you are not working with image data.
Stars
44
Forks
2
Language
Python
License
MIT
Category
Last pushed
Jul 11, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Correr-Zhou/SPML-AckTheUnknown"
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