An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale (Paper Explained)
Why it's on BrighterTube
Hand-picked by a BrighterTube curator · found via round-3 back catalogue of a channel Lumen picks video by video · 82% confidenceExplains Vision Transformers (ViT), applying pure transformer architecture to image recognition at scale. Teaches how attention mechanisms work on visual data without convolutions.
What you'll learn
A 30-minute video from Yannic Kilcher: “An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale (Paper Explained)”.
Video by Yannic Kilcher, played through YouTube's embedded player.
Part of Computer Vision, Deep Learning Architectures, Papers Explained