The Vision Spectra Conference is now available ON DEMAND: Discover emerging trends in Cameras, Systems, and Sensors!
Search
Menu
Lambda Research Optics, Inc. - DFO
Photonics Dictionary

vision-transformer networks

Vision transformer (ViT) networks are neural network architectures that apply the Transformer architecture, originally developed for natural language processing, to the task of processing visual data. Unlike traditional convolutional neural networks (CNNs), which dominate in computer vision tasks, ViTs use self-attention mechanisms and multi-layer perceptrons (MLPs) to process image patches directly.

Key features of vision transformer networks include:

Patch embedding: Input images are divided into fixed-size patches, which are linearly embedded into lower-dimensional vectors.

Transformer encoder: These embedded patches are then processed by a stack of Transformer encoder layers. Each layer includes self-attention mechanisms to capture relationships between patches and MLPs for non-linear transformations.

Global context: ViTs can capture global context information through self-attention, which helps in understanding relationships between distant patches.

Classification head: Typically, a classification head is added on top of the Transformer encoder to produce final predictions for image classification tasks.

Vision transformer networks have shown promising results in various benchmarks and tasks, demonstrating their potential as an alternative to traditional CNNs for computer vision applications.
 

Explore Our Content
News
Features
Latest Products
Webinars
White Papers
All Things Photonics Podcast
Videos
Our Summits & Conferences
Industry Events
Bookstore
Join Our Community
Subscribe
Advertise
Become a member
Sign in
Contribute a Feature
Suggest a Webinar
Submit a Press Release
Mobile Apps

About Us
Our Company
Our Publications
Contact Us
Career Opportunities
Teddi C. Laurin Scholarship

Terms & Conditions
Privacy Policy
California Consumer Privacy Act (CCPA)



©2024 Photonics Media
100 West St.
Pittsfield, MA, 01201 USA
[email protected]
We use cookies to improve user experience and analyze our website traffic as stated in our Privacy Policy. By using this website, you agree to the use of cookies unless you have disabled them.