zhmiao/OpenLongTailRecognition-OLTR

Pytorch implementation for "Large-Scale Long-Tailed Recognition in an Open World" (CVPR 2019 ORAL)

48
/ 100
Emerging

This tool helps computer vision researchers accurately identify objects in images, even when some objects appear very rarely in datasets. You feed in a large collection of images, and it outputs an improved image recognition model that can better classify both common and uncommon objects. This is primarily for researchers and practitioners working on advanced image recognition tasks with imbalanced datasets.

869 stars. No commits in the last 6 months.

Use this if you are building an image recognition system where some object categories have significantly fewer training examples than others, and you need to accurately identify all categories, including the rare ones.

Not ideal if your image datasets are well-balanced across all categories, or if you are looking for a plug-and-play solution without deep involvement in model training.

image-recognition computer-vision imbalanced-data object-classification machine-learning-research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 22 / 25

How are scores calculated?

Stars

869

Forks

130

Language

Python

License

BSD-3-Clause

Last pushed

Jul 16, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/zhmiao/OpenLongTailRecognition-OLTR"

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