AntonotnaWang/HINT

[CVPR 2022] HINT: Hierarchical Neuron Concept Explainer

22
/ 100
Experimental

This tool helps machine learning researchers and practitioners understand how image classification models 'think' by identifying which parts of the neural network are responsible for detecting specific visual concepts, from concrete objects like 'dog' to abstract categories like 'animal'. You input a pre-trained image classification model and image datasets, and it outputs insights into neuron activation for various concepts, along with visualizations of how the model localizes these concepts within images.

No commits in the last 6 months.

Use this if you need to systematically and quantitatively analyze the internal workings of vision models, especially to debug their behavior or interpret their predictions by linking internal neurons to human-understandable concepts.

Not ideal if you are looking for a tool to improve model accuracy or for general model development and training, as its focus is on interpretability, not performance optimization.

deep-learning-interpretability computer-vision neural-network-analysis explainable-ai image-recognition
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

20

Forks

Language

Jupyter Notebook

License

MIT

Last pushed

Apr 19, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/AntonotnaWang/HINT"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.