Lextal/SotA-CV

A repository of state-of-the-art deep learning methods in computer vision

46
/ 100
Emerging

This project helps computer vision researchers and practitioners quickly find the best deep learning models for various image analysis tasks. It provides a curated collection of state-of-the-art results for tasks like semantic segmentation, object detection, and image classification, showing what goes in (an image) and what comes out (the processed image or analysis). Researchers and engineers working on computer vision applications would use this to inform their model selection and comparative studies.

196 stars. No commits in the last 6 months.

Use this if you need to quickly identify top-performing deep learning models for specific computer vision tasks and datasets, or to compare your own research results against established benchmarks.

Not ideal if you are looking for ready-to-use code implementations or pre-trained models, as this project focuses on aggregating quantitative evaluation results.

computer-vision-research image-analysis deep-learning-benchmarking model-comparison algorithm-selection
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

196

Forks

34

Language

License

MIT

Last pushed

Jul 06, 2018

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Lextal/SotA-CV"

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