Duration 18:43
16+
Play
Video

How synthetic datasets can help train real-world computer vision models

Cesar Romero
Principal Machine Learning Engineer at Unity Technologies
  • Video
  • Video
VentureBeat Transform 2020
July 17, 2020, Online
VentureBeat Transform 2020
Request Q&A
Video
How synthetic datasets can help train real-world computer vision models
Available
In cart
Free
Free
Free
Free
Free
Free
Add to favorites
10
I like 0
I dislike 0
Available
In cart
Free
Free
Free
Free
Free
Free
  • Description
  • Discussion

About speaker

Cesar Romero
Principal Machine Learning Engineer at Unity Technologies

Software developer interested in artificial intelligence, data analysis and visualization. I believe the best software is open source. Most comfortable programming in Python, Java and some C++.Most interested in: Artificial Intelligence, Machine Learning, Big Data.

View the profile

About the talk

Deep learning models can perform significantly better when trained on very large datasets. Manually labeling large collections of real-world pictures is expensive and may not include outlier scenarios that can be relevant for models expected to work on complex environments. One way to tackle this problem is to use synthetic data which can be generated by simulating relevant scenarios using a game engine. And this can be applied in many industries, not just the gaming industry.

In this talk, Unity’s principal ML engineer will explore recent advances in machine learning and explain the role game engines play in the future of computer vision. He’ll summarize existing tools that can be used to generate perfectly labeled synthetic datasets for different perception tasks to reduce the cost of acquiring the labeled examples needed to train the model. It is still early days, but several research projects published in top conferences show how, in some cases, a model trained on real-world data is outperformed by a model trained on 100% synthetic data at a fraction of the cost. Cesar will provide takeaways to executives in other industries about how they can leverage these findings.

Share

Cackle comments for the website

Buy this talk

Access to the talk “How synthetic datasets can help train real-world computer vision models”
Available
In cart
Free
Free
Free
Free
Free
Free

Ticket

Get access to all videos “VentureBeat Transform 2020”
Available
In cart
Free
Free
Free
Free
Free
Free
Ticket

Interested in topic “Artificial Intelligence and Machine Learning”?

You might be interested in videos from this event

July 15 - 17, 2020
Online
51
4 K
ai, automl, big data, roi, rpa, technology

Similar talks

Shaun Moore
CEO and Founder at Trueface
+ 1 speaker
Hari Sivaraman
Head of AI & Data Content Strategy at Venturebeat
+ 1 speaker
Available
In cart
Free
Free
Free
Free
Free
Free
Carla Saavedra Kochalski
Sr. Director, Enterprise Customer Experiences at Capital One
+ 5 speakers
Timnit Gebru
Research Scientist at Google AI; Black in AI
+ 5 speakers
Francesca Rossi
IBM Fellow and AI Ethics Global Leader at IBM Research
+ 5 speakers
Jaime Fitzgibbon
Innovation Strategist & Director at San Francisco Innovation Hub, Booz Allen Hamilton
+ 5 speakers
Huma Abidi
Senior Director of AI SW Products and Engineering at Intel Corporation
+ 5 speakers
Kay Firth-Butterfield
Head of AI and Machine Learning at World Economic Forum
+ 5 speakers
Available
In cart
Free
Free
Free
Free
Free
Free
Andrea Rene
Experienced Speaker and Fundraising Coordinator
+ 5 speakers
Gina Joseph
Vice President, Strategy & Partnerships at VentureBeat
+ 5 speakers
Michele Romanow
Co-founder at Clearbanc
+ 5 speakers
Anima Anandkumar
Director of ML Research at NVIDIA
+ 5 speakers
Carly Eckert
Chief Clinical Officer at Greenlight Ready
+ 5 speakers
Kate Kallot
Head of Emerging Areas at NVIDIA
+ 5 speakers
Available
In cart
Free
Free
Free
Free
Free
Free

Buy this video

Video

Access to the talk “How synthetic datasets can help train real-world computer vision models”
Available
In cart
Free
Free
Free
Free
Free
Free

Conference Cast

With ConferenceCast.tv, you get access to our library of the world's best conference talks.

Conference Cast
577 conferences
23231 speakers
8691 hours of content