Semantic segmentation, or image segmentation, clusters parts of an image together that belong to the same object class. Today, this computer vision task is being used in a wide variety of applications including self-driving cars, medical imaging, and virtual fitting rooms.
The process of selecting the right semantic segmentation architecture and deploying it successfully can be tedious and time-consuming. In this AMA with Yonatan Geifman and Lior Kadoch, you will:
- Hear from the deep learning community some challenges in choosing the optimal segmentation architecture
- Learn the main considerations and best practices when selecting segmentation models
- Understand the common issues in deploying segmentation models on edge devices and how to overcome them