Transformers for Computer Vision

Over the last few years, the field of AI has been revolutionized by the emergence of transformer models. In this course, we will study transformer models for various computer vision problems. The course will consist of research paper presentations, interactive exercises, research paper discussions, and a semester-long course project. Topics will include transformer architectures for images and videos, efficient transformer model design, data-efficient learning, self-supervised learning, multimodal learning, image generation, and others. This course is a semester-long 3-credit course, appropriate for graduate students and advanced undergraduate students with an interest in applying transformer models to computer vision.