Data Augmentation and Optimized Architectures for Computer Vision - Fatih Porikli - 635 скачать в хорошем качестве

Data Augmentation and Optimized Architectures for Computer Vision - Fatih Porikli - 635

Today we kick off our coverage of the 2023 CVPR conference joined by Fatih Porikli, a Senior Director of Technology at Qualcomm. In our conversation with Fatih, we covered quite a bit of ground, touching on a total of 12 papers/demos, focusing on topics like data augmentation and optimized architectures for computer vision. We explore advances in optical flow estimation networks, cross-model, and stage knowledge distillation for efficient 3D object detection, and zero-shot learning via language models for fine-grained labeling. We also discuss generative AI advancements and computer vision optimization for running large models on edge devices. Finally, we discuss objective functions, architecture design choices for neural networks, and efficiency and accuracy improvements in AI models via the techniques introduced in the papers. 🔔 Subscribe to our channel for more great content just like this: https://youtube.com/twimlai?sub_confi... 📖 CHAPTERS =============================== 00:01:03 - Background 00:03:51 - Data augmentation techniques 00:07:15 - AI needs efficient architectures, data & memory 00:14:37 - Optical flow: tracking movement between frames 00:25:48 - Improving optical flow through DIFT 00:37:12 - Imitation learning with capable and limited networks 00:42:48 - Generating 3D data without manual labeling 00:50:21 - Image conditioning controls AI-generated images 00:54:08 - Generative AI is changing everything in Computer Vision 🗣️ CONNECT WITH US! =============================== Subscribe to the TWIML AI Podcast: https://twimlai.com/podcast/twimlai/ Join our Slack Community: https://twimlai.com/community/ Subscribe to our newsletter: https://twimlai.com/newsletter/ Want to get in touch? Send us a message: https://twimlai.com/contact/ 🔗 LINKS & RESOURCES =============================== Paper: DistractFlow: Improving Optical Flow Estimation Models via Realistic Distractions and Pseudo-Labeling Paper: Déjà vu: Regenerative Learning to Enhance Dense Prediction For the complete resource list (10 more papers!), head over to https://twimlai.com/go/635 📸 Camera: https://amzn.to/3TQ3zsg 🎙️Microphone: https://amzn.to/3t5zXeV 🚦Lights: https://amzn.to/3TQlX49 🎛️ Audio Interface: https://amzn.to/3TVFAIq 🎚️ Stream Deck: https://amzn.to/3zzm7F5