GithubHelp home page GithubHelp logo

nducthang / active-learning-for-object-detection Goto Github PK

View Code? Open in Web Editor NEW
47.0 3.0 4.0 555.29 MB

Active learning for deep object detection using YOLO

Python 30.38% Shell 0.03% Jupyter Notebook 69.58%
yolov5 semi-supervised-learning active-learning interactive-learning object-detection

active-learning-for-object-detection's Introduction

Active-learning-for-object-detection

Active learning for deep object detection using YOLO

In this project, I study the active learning method for object detection. Specifically, I have active field experiments for weapon detection.

Today, the amount of data for deep learning is increasing, but the manpower to label it is not enough. Therefore, the problem is how to use as little data as possible and still achieve high efficiency for the model. That is why I study actively.

In the active learning method, the person labels the data, which is then fed into the training model. The model then goes on to pick out a small amount of unlabeled data that it thinks after being labeled, it gets better. And give it to the labeler. And the loop goes on like that.

Because of human interaction, object detection model requires speed to be fast and accuracy is also relative. Through experimentation I have chosen YOLO v5.

Theoretical details please see attached pdf report.

active-learning-for-object-detection's People

Contributors

nducthang avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar

active-learning-for-object-detection's Issues

run instructions?

Hello,

Thank you for sharing this exciting project.

I would like to know if there's any instructions to run this project!

I was trying to run it but unfortunately I failed :(

Thank you very much

Does it work?

The theory behind this project is interesting and I have been wondering if it would be worth trying in my own projects, but I didn't want to waste my time if it doesn't work. Do you end up building a model that can detect the correct class of objects beyond the scope of the original training data or do you end up with a ton of false positives as the system has no way of self-correcting? Does it end up going the opposite direction and overfitting? I would be interested in hearing how it worked out for you

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.