Course contents: The course introduces students to the fundamental concepts and applications of Computer Vision, with a focus on Deep Learning techniques. It examines how computers perceive and interpret the visual world through modern methods such as Convolutional Neural Networks (CNNs), Vision Transformers, and generative models (VAEs, Diffusion).Special emphasis is placed on developing applications that combine understanding, creation, and interaction with visual data, as well as multimodal applications integrating images and natural language (e.g., CLIP).

At the end of the course the student will be able to:

• Describe the fundamental principles, challenges, and applications of computer vision.
• Analyze and implement Convolutional Neural Networks (CNNs) and Vision Transformers for image processing tasks.
• Apply transfer learning techniques for image classification, object detection, and segmentation.
• Develop and evaluate basic generative models, such as Variational Autoencoders (VAEs) and Dif-fusion Models.
• Integrate visual and textual data in multimodal applications using models like CLIP.
• Incorporate computer vision systems into practical applications.

Assessment: Course evaluation is based on short assignments and/or a midterm progress assessment during the semester, with a total weight of up to 40%. The final semester project (code and technical report) accounts for 60%. These percentages may vary (by up to ±10%) from year to year. To pass the course, students must achieve a passing grade both in the final project and in the overall grade. The assignments may be accompanied by an oral examination.