The Startup
Published in

The Startup

Object Detection With Synthetic Data

Reduce the domain gap with domain randomization

In this post, we’ll explore how we can improve the accuracy of object detection models that have been trained solely on synthetic data.

Why machine learning? Why simulate data?

Since the resurgence of deep learning for computer vision through AlexNet in 2012, we have seen improvement after improvement — deeper networks, new architectures, more availability in data — with records being broken for accuracy and…

--

--

--

Get smarter at building your thing. Follow to join The Startup’s +8 million monthly readers & +756K followers.

Recommended from Medium

NLP (natural language processing)

Neural Networks: A Simple Concept Explainer

Converging minds at SysML 2019

Introduction to Random Forest

Rocchio and KNN — Job post detection

Neural Engineering, NER ’19 Notes

Neural network pruning with simulated annealing

How to scale the machine learning community to 1 Million researchers

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
Neurolabs

Neurolabs

We help retailers automate time-consuming and costly business processes using Synthetic Computer Vision.

More from Medium

Review — Google’s Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation

Introduction to PyTorch with Tutorial

Getting Started with PyTorch Image Models (timm): a practitioner’s guide

MLPerf: Intel and Deci Boost NLP Models — Reaching Faster and More Accurate Inference Performance