Git Product home page Git Product logo

jnn_detection's Introduction

Joint Neural Networks for One-shot Object Detection (Under construction, soon to be updated)

This is the implementation of the "Joint Neural Networks for One-shot Object Recognition and Detection" thesis by Camilo Vargas.

Requirements

Usage

Set the training and testing parameters in python params/config.py file. Run the python main.py file to train/test the defined configuration.

Results

Joint neural network performance for one-shot object detection tested on the VOC dataset, leaving four unseen classes:

Method / class cow sheep cat aeroplane mAP
JNN 64.7 51.0 65.2 43.5 69.1

Joint neural network performance for one-shot object detection trained on the COCO dataset, tested on the VOC dataset:

Method / class plant sofa tv car bottle boat chair person bus train horse bike dog bird mbike table cow sheep cat aero mAP
JNN 9.5 69.3 49.8 60.3 7.2 29.1 10.1 6.7 60.3 57.2 58.5 45.3 62.6 45.6 74.8 29.0 70.4 55.4 54.4 88.1 47.1

Testing on the top performing Open-Logodataset classes and the mAP results for the whole dataset

Class AP / mAP
anz_text 100.00
rbc 98.86
blizzardentertainment 98.34
costco 93.26
3m 90.61
bosch_text 90.00
gap 89.47
lexus 88.92
generalelectric 83.32
hp 82.81
levis 79.36
airhawk 79.17
danone 79.02
armitron 77.73
google 77.66
all 52.84

Reference

Joint Neural Networks for One-shot ObjectRecognition and Detection. Camilo Jose Vargas Cortes. School of Electronic Engineering and Computer Science. Queen Mary University of London. 2020.

Examples

acknowledgement

This code is based on the following repositories:

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.