bmezaris/TAME
Code and data for our learning-based eXplainable AI (XAI) method TAME: M. Ntrougkas, N. Gkalelis, V. Mezaris, "TAME: Attention Mechanism Based Feature Fusion for Generating Explanation Maps of Convolutional Neural Networks", Proc. IEEE Int. Symposium on Multimedia (ISM), Naples, Italy, Dec. 2022.
This project helps image analysis practitioners understand why an existing AI model made a specific decision. You provide an image and the classification given by your AI, and it generates an 'explanation map' that highlights the exact regions in the image that led to that classification. This is useful for anyone using or auditing AI-powered image classification systems, such as medical professionals analyzing scans or quality control engineers inspecting products.
No commits in the last 6 months.
Use this if you need to visualize the specific parts of an image that your Convolutional Neural Network (CNN) focused on to arrive at a particular classification.
Not ideal if you are looking to train a new image classification model from scratch or if you need explanations for non-image-based AI models.
Stars
7
Forks
1
Language
Python
License
—
Last pushed
Dec 01, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/bmezaris/TAME"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
obss/sahi
Framework agnostic sliced/tiled inference + interactive ui + error analysis plots
tensorflow/tcav
Code for the TCAV ML interpretability project
MAIF/shapash
🔅 Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent...
TeamHG-Memex/eli5
A library for debugging/inspecting machine learning classifiers and explaining their predictions
csinva/imodels
Interpretable ML package 🔍 for concise, transparent, and accurate predictive modeling...