Код: 365481

Назва:

Комп`ютерний зір

Анотація: This course offers an in-depth exploration of computer vision, focusing on critical models such as Convolutional Neural Networks (CNNs), Vision Transformers (ViTs), and other significant architectures. It covers image classification, object detection, segmentation, and video understanding, emphasizing practical application through advanced projects. Recommended prerequisites: strong foundation in linear algebra and statistics, a completed undergraduate-level Machine Learning course.


Рекомендована література: Основна:
1. Szeliski, R. Computer Vision: Algorithms and Applications (2nd ed.). Springer, 2022.
2. Zhang, R., Isola, P., Efros, A. A., Shechtman, E., & Wang, O. The Unreasonable Effectiveness of Deep Features as a Perceptual Metric (LPIPS). CVPR, 2018. (still widely used for generative evaluation; include if you discuss metrics)
3. Stanford CS231n (latest iteration notes/assignments), 2021–present (high-quality teaching reference).
4. Dosovitskiy, A., et al. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale (ViT). ICLR, 2021.
Допоміжна:
1. Hugging Face Diffusers documentation (pipelines, schedulers, training recipes), 2025.
2. Oquab, M., et al. DINOv2: Learning Robust Visual Features without Supervision. 2023.
3. . Kirillov, A., et al. Segment Anything. 2023