adursun/wsddn.pytorch

Implementation of Weakly Supervised Deep Detection Networks using the latest version of PyTorch

51
/ 100
Established

This project helps computer vision researchers and practitioners automatically identify and locate multiple objects within an image, even with limited labeled data. You provide images with only general labels (e.g., "there's a cat here," not "the cat is at these exact coordinates"), and it outputs bounding box predictions for various objects. This is useful for those working on object detection tasks in research or development.

Use this if you need to perform object detection in images and want to leverage weakly supervised learning to reduce the burden of precise data annotation.

Not ideal if you already have finely annotated datasets with exact bounding box coordinates for all objects, or if you are looking for a plug-and-play solution without any development work.

object-detection computer-vision image-analysis weakly-supervised-learning deep-learning-research
No Package No Dependents
Maintenance 10 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

50

Forks

10

Language

Python

License

Apache-2.0

Last pushed

Mar 13, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/adursun/wsddn.pytorch"

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