Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

YouTube

Perception Encoder and Improving Visual Understanding

Roboflow via YouTube

Start learning Write review
Datacamp Ad

AI Engineer - Learn how to integrate AI into software applications

Learn More → Coursera Ad

Gain a Splash of New Skills - Coursera+ Annual Just ₹7,999

Learn More →

Overview

Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Join Daniel Bolya, Scientific Researcher at Meta, for a comprehensive 43-minute webinar exploring Perception Encoder, a cutting-edge family of models designed to enhance visual understanding and improve text-to-image search relevancy. Discover the story behind Perception Encoder's development and learn about its advanced capabilities for measuring similarity between images and text. Watch live demonstrations comparing search query performance and see how this technology integrates with Roboflow's platform. Explore real-world applications of Perception Encoder across various industries and participate in an interactive Q&A session. The session covers the fundamental concepts of visual embeddings, practical implementation examples, and hands-on testing of search comparisons, making it valuable for researchers, developers, and professionals working in computer vision, machine learning, and image search technologies.

Syllabus

00:00 Introduction - Need Better Image Search?
02:15 What is Perception Encoder?
06:52 Example: Measuring Image & Text Similarity with Perception Encoder
11:15 Demo: Testing & Comparing Search Queries Comparisons
26:09 Integrating Perception Encoder with Roboflow
27:28 Real-World Applications of Perception Encoder?
33:11 Viewer Q&A

Taught by

Roboflow

Reviews

4.0 rating, based on 1 Class Central review

Start your review of Perception Encoder and Improving Visual Understanding

  • Profile image for Olatuji Banjo
    Olatuji Banjo
    This was a great introductory course on Class Central. As a beginner, I appreciated how clearly the instructor explained the concepts behind Perception Encoder. They really did justice to the topic.

    One thing that could be improved is the model’s counting ability, which was a noticeable limitation.

    Overall, I’d recommend this course to anyone new to visual understanding or interested in learning how models like Perception Encoder work.
Start learning

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Sign up for free
Someone learning on their laptop while sitting on the floor.