Do Vision Transformers See Like Convolutional Neural Networks? | Paper Explained

❤️ Become The AI Epiphany Patreon ❤️ ► https://www.patreon.com/theaiepiphany In this video I cover the "Do Vision Transformers See Like Convolutional Neural Networks?" paper. They dissect ViTs and ResNets and show the differences in the features learned as well as what contributes to those differences (like the amount of data used, skip connections, etc.). ▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬ ✅ Paper: https://arxiv.org/abs/2108.08810 ▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬ ⌚️ Timetable: 00:00 Intro 00:45 Contrasting features in ViTs vs CNNs 06:45 Global vs Local receptive fields 13:55 Data matters, mr. obvious 17:40 Contrasting receptive fields 20:30 Data flow through CLS vs spatial tokens 23:30 Skip connections matter a lot in ViTs 24:20 Spatial information is preserved in ViTs 30:10 Features evolution with the amount of data 32:20 Outro ▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬ 💰 BECOME A PATREON OF THE AI EPIPHANY ❤️ If these videos, GitHub projects, and blogs help you, consider helping me out by supporting me on Patreon! The AI Epiphany ► https://www.patreon.com/theaiepiphany One-time donation: https://www.paypal.com/paypalme/theaiepiphany Much love! ❤️ Huge thank you to these AI Epiphany patreons: Eli Mahler Petar Veličković Zvonimir Sabljic ▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬ 💡 The AI Epiphany is a channel dedicated to simplifying the field of AI using creative visualizations and in general, a stronger focus on geometrical and visual intuition, rather than the algebraic and numerical "intuition". ▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬ 👋 CONNECT WITH ME ON SOCIAL LinkedIn ► https://www.linkedin.com/in/aleksagordic/ Twitter ► https://twitter.com/gordic_aleksa Instagram ► https://www.instagram.com/aiepiphany/ Facebook ► https://www.facebook.com/aiepiphany/ 👨‍👩‍👧‍👦 JOIN OUR DISCORD COMMUNITY: Discord ► https://discord.gg/peBrCpheKE 📢 SUBSCRIBE TO MY MONTHLY AI NEWSLETTER: Substack ► https://aiepiphany.substack.com/ 💻 FOLLOW ME ON GITHUB FOR ML PROJECTS: GitHub ► https://github.com/gordicale