ExplainableML/ACVC

Official PyTorch implementation of CVPRW 2022 paper "Attention Consistency on Visual Corruptions for Single-Source Domain Generalization"

23
/ 100
Experimental

This project helps machine learning engineers or researchers improve how well their computer vision models perform when faced with new, unseen types of images. It takes a dataset of natural images, applies advanced data augmentation techniques and a specialized 'attention consistency' method, and outputs a more robust image classification model. This is for users who need their models to generalize effectively from a single source of training data to diverse target domains like paintings, cliparts, or sketches.

No commits in the last 6 months.

Use this if you need your image recognition models to maintain high accuracy even when deployed in environments with visually different data than what they were trained on.

Not ideal if you are looking for a general-purpose machine learning library rather than a specific solution for domain generalization in computer vision.

computer-vision image-recognition machine-learning-research domain-adaptation data-augmentation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

29

Forks

Language

Python

License

MIT

Last pushed

Feb 22, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/ExplainableML/ACVC"

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