How Active Learning Improves Nighttime Pedestrian Detection

4 years ago Posted in

Active learning makes it possible for AI to automatically choose the right training data. An ensemble of dedicated DNNs goes through a pool of image frames, flagging frames that it finds to be confusing. These frames are then labeled and added to the training dataset. This process can improve DNN perception in difficult conditions, such as nighttime pedestrian detection.

https://www.youtube.com/watch?v=2jFysE5x7zs

Nicolas Leszczynski, Principal Solution Engineer at Riverbed, discusses the results of the recent...

AI cloud platform promises sustainable compute

Alex Sharp, Chief Projects Officer, Data Centres at Nscale, outlines the scale of the AI data...

AI Transform - Interview with NetApp

Kirsty Biddiscombe, AI, ML and Data Analytics lead for NetApp EMEA, discusses the challenges and...

Analytics and AI - the perfect combination

Iju Raj, Executive Vice President R&D and Simon Bennett, Director, Research and Innovation, both at...

Absolics finds semiconductor Solace

Tom Fairbairn, Distinguished Engineer at Solace, explains how Absolics is using the Solace PubSub+...

AI - turning the challenge into a business opportunity

Dr Clare Walsh, Director of Education at the Institute of Analytics (IoA), and one of the of the...

AI-First approach provides innovation success

Steve Young, UK SVP and MD, Dell Technologies, explains how can businesses can navigate the high...

AI regulation - a delicate balancing act?

Ivana Bartoletti, Global Chief Privacy and AI Governance Officer at Wipro, also a Council of Europe...

© 2024 - Angel Business Communications Limited

Made with by Angels