Leveraging Gen AI in Computer Vision

Leveraging Gen AI in Computer Vision

Are you intrigued by the possibilities of AI in computer vision? Join us for a tech talk exploring cutting-edge techniques for object detection.

What to Expect:

• Zero-Shot Learning: Discover the magic of foundation models that possess inherent knowledge about various objects, enabling them to label your image data effortlessly.
• Advanced Vision Transformers: Uncover the potential of sophisticated transformer architectures like OWL-ViT (Open-World Language-Vision Transformer) that bridge the gap between language and vision, understanding object descriptions without extensive training.
• Efficient Object Detection: Learn how to leverage powerful object detection models like YOLO-NAS (Neural Architecture Search) for real-time performance, all while minimizing computational resources.
• Code Examples: Witness the simplicity of training your custom object detection model with minimal coding effort, leveraging state-of-the-art AI tools and techniques.

Who Should Attend:

• AI Enthusiasts: Anyone fascinated by the advancements in computer vision and object detection.
• Developers and Researchers: Gain practical knowledge and insights into building efficient and effective object detection systems.
• Tech-Savvy Individuals: Expand your AI expertise and discover how to create impactful vision applications.

Speaker:
Daniel Bank

Agenda:
6:00p - 7:00p - Vector Search with Google's Vertex AI