Designing Efficient Vision Transformer Networks for Autonomous Vehicles
Offer
Transformer networks have been proven to achieve better accuracy in a variety of autonomous vehicle perception tasks when compared to convolutional neural networks running on embedded systems.
Join this informative webinar to explore design principles for efficient transformers in production, demonstrated by two dense prediction applications–depth estimation and semantic segmentation–running on NVIDIA DRIVE Orin. We’ll also explain how innovative model design can significantly reduce both model size and inference latency while achieving better accuracy in AV perception.
Join this informative webinar to explore design principles for efficient transformers in production, demonstrated by two dense prediction applications–depth estimation and semantic segmentation–running on NVIDIA DRIVE Orin. We’ll also explain how innovative model design can significantly reduce both model size and inference latency while achieving better accuracy in AV perception.
Select one of the following webinars
THANK YOU FOR REGISTERING FOR THE WEBINAR
You will receive an email with instructions on how to join the webinar shortly.
Main Content
maincontent goes here
Content
Content goes here
Content
content goes here
Content
Content goes here
Content
DGX Station Whitepaper
Dive deeper into the DGX Station and learn more about the architecture, NVLink, frameworks, tools and more.
Dive deeper into the DGX Station and learn more about the architecture, NVLink, frameworks, tools and more.
DGX Station Whitepaper
Dive deeper into the DGX Station and learn more about the architecture, NVLink, frameworks, tools and more.
Dive deeper into the DGX Station and learn more about the architecture, NVLink, frameworks, tools and more.
Content
Content goes here
Speakers
Le An
Senior Deep Learning Software Engineer, NVIDIALe has extensive experience in machine learning, deep learning, and computer vision techniques for solving real-world problems in autonomous driving, video intelligence, image analysis, and more. He received his Ph.D. from the University of California, Riverside, an M.S. from Eindhoven University of Technology in the Netherlands, and a B.Eng. from Zhejiang University, China.
John Yang
Senior Deep Learning Software Engineer, NVIDIAJohn's background mostly lies in using machine learning and computer vision (CV), to solve real-world problems. He has worked on various CV projects/researches with Samsung and Korean National Defense while pursuing his Ph.D. in intelligent systems. He received his B.S. from the University of Michigan-Ann Arbor, as well as both an M.S and Ph.D from Seoul National University.
Text here
Text here
Text here
Text here
Other Speakers
Name1
Job Title.
Job Title.
Name 2
Job Title.
Job Title.
Name 3
Job Title.
Job Title.
Main CTA for lightbox form use class="lightbox" CTA
Content Title
Content here