ziplab/LIT

[AAAI 2022] This is the official PyTorch implementation of "Less is More: Pay Less Attention in Vision Transformers"

40
/ 100
Emerging

This project provides optimized AI models for analyzing images efficiently. It takes in images and outputs classifications (e.g., 'cat,' 'dog'), detected objects with bounding boxes (e.g., 'car' at coordinates X, Y), or segmented regions (e.g., outlining a 'tree'). This tool is for AI practitioners and researchers who build or deploy computer vision systems and need high performance.

No commits in the last 6 months.

Use this if you are developing computer vision applications for image classification, object detection, or semantic segmentation and need a model that balances accuracy with computational efficiency.

Not ideal if you are looking for a plug-and-play solution without any AI model development or fine-tuning, or if your tasks do not involve processing visual data.

image-classification object-detection semantic-segmentation computer-vision machine-learning-engineering
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

97

Forks

13

Language

Python

License

Apache-2.0

Last pushed

Jun 19, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/ziplab/LIT"

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