Computer Vision: Vision Transformers & Vision Language Model

About this course

This course contains the use of artificial intelligenceDisclosure: AI tools were used only to assist in creating the course outline and course thumbnail. All instructional content, explanations, and project walkthroughs were fully created manually by the instructor.Welcome to Computer Vision: Vision Transformers & Vision Language Model course. This is a comprehensive project based course where you will learn how to build modern computer vision applications using Vision Transformers, Segment Anything Model, Contrastive Language Image Pre Training, attention mechanism, and other AI models. This course is a perfect combination between artificial intelligence and computer vision, making it an ideal opportunity for you to practice your programming skills while improving your technical knowledge in deep learning. In the introduction session, you will learn the basic fundamentals of Vision Transformers and Vision Language Model, such as getting to know its use cases and how the system works. Then, in the next section, we will start the projects, in the first project, we are going to build a satellite image classification system using Vision Transformers. This system will be able to analyze satellite images and categorize different land types, for example, forests, rivers, residential areas, industrial areas, and highways. Then, in the second project, we are going to build a soil type classification system using Vision Transformers. This system will enable us to analyze soil images and classify different soil categories like black soil, clay soil, red soil, and other soil types. Afterward, in the third project, we are going to perform image segmentation using the Segment Anything Model. Firstly, we will remove product backgrounds by isolating the main object from its surrounding environment to create clean product images for e-commerce. After that, we will also segment flood areas by identifying and separating water affected regions from aerial images to support disaster monitoring and analysis. Then