Edge AI in Action: Technologies and Applications
Image credit: CVPR 2025Edge AI refers to the deployment of artificial intelligence models directly on edge devices—such as smartphones, cameras, sensors, drones, and wearables—enabling them to perform inference locally without continuous reliance on the cloud. This paradigm offers several significant benefits, including reduced latency, enhanced privacy, increased responsiveness, and improved energy efficiency.
However, building performant AI systems for edge environments introduces unique challenges. These include model compression, quantization, distillation, pruning, and runtime optimization, as well as effective orchestration across heterogeneous hardware in hybrid edge–cloud architectures.
In this CVPR 2025 tutorial, we offered a hands-on and practice-oriented guide to designing, optimizing, and deploying deep learning models for edge AI. Focusing on computer vision tasks, we explored real-world use cases, including hand gesture recognition, object detection, and large language models. The tutorial emphasized multimodal AI, integrating inputs such as video, images, and text to enable intelligent, interactive systems.
We demonstrated the use of leading tools and frameworks, including ONNX, Qualcomm SNPE, TensorFlow Lite for Android, vLLM, and Ollama, across a range of hardware platforms, such as Jabra intelligent cameras, Qualcomm dev boards, Android mobile phones, and NVIDIA Jetson AGX Orin. Attendees gained actionable insights into the end-to-end pipeline of edge AI, from model design to real-time deployment.
Music City Center
201 Rep. John Lewis Way S, Nashville, 37203 Tennessee
