yinboc/DGP
Rethinking Knowledge Graph Propagation for Zero-Shot Learning, in CVPR 2019
This project helps computer vision researchers expand the capabilities of image recognition systems to identify entirely new categories of objects they haven't been specifically trained on. It takes existing image classification models and knowledge graphs (like WordNet) as input and outputs an enhanced model capable of 'zero-shot learning' — recognizing objects from unseen classes. This is for researchers and practitioners in machine learning and computer vision who need to build more adaptable and generalized image recognition systems.
321 stars. No commits in the last 6 months.
Use this if you are developing computer vision models and need to enable them to recognize object categories they have never encountered during training, leveraging semantic relationships between concepts.
Not ideal if you are looking for an out-of-the-box solution for standard image classification where all target classes are known and available for training.
Stars
321
Forks
57
Language
Python
License
MIT
Category
Last pushed
Jun 22, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/yinboc/DGP"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
pyg-team/pytorch_geometric
Graph Neural Network Library for PyTorch
a-r-j/graphein
Protein Graph Library
raamana/graynet
Subject-wise networks from structural MRI, both vertex- and voxel-wise features (thickness, GM...
pykale/pykale
Knowledge-Aware machine LEarning (KALE): accessible machine learning from multiple sources for...
dmlc/dgl
Python package built to ease deep learning on graph, on top of existing DL frameworks.