AngelosNal/Vision-DiffMask
Official PyTorch implementation of Vision DiffMask, a post-hoc interpretation method for vision models.
This tool helps you understand why an AI model made a specific decision when classifying an image. You provide an image and the AI's classification, and it highlights the crucial parts of the image that led to that classification. This is useful for AI researchers or developers who need to debug or build trust in their image classification models.
No commits in the last 6 months.
Use this if you need to explain the reasoning of a Vision Transformer image classification model by identifying the most influential parts of an input image.
Not ideal if you are working with non-image data, or if your AI model is not a Vision Transformer for classification.
Stars
32
Forks
3
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Mar 05, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/AngelosNal/Vision-DiffMask"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
sp-nitech/diffsptk
A differentiable version of SPTK
trigeorgis/mdm
A TensorFlow implementation of the Mnemonic Descent Method.
clovaai/mxfont
Official PyTorch implementation of MX-Font (Multiple Heads are Better than One: Few-shot Font...
clovaai/fewshot-font-generation
The unified repository for few-shot font generation methods. This repository includes FUNIT...
Michedev/DDPMs-Pytorch
Implementation of various DDPM papers to understand how they work