Lecture: Deep Learning for Computer Vision I: Basics

Lecture shared among multiple lecturers. I contributed to the installments: SS2020, SS2021, SS2024, SS2025

This lecture series provides a comprehensive journey through modern deep learning and computer vision. It begins with an introduction to neural networks, covering foundational concepts, optimization techniques, and regularization. The course then dives into deep convolutional networks, exploring their role in object recognition, detection, and segmentation. It extends to sequential modeling with recurrent neural networks and embeddings, applying them to tasks like image captioning and tagging. Advanced topics include action recognition, self-supervised learning, and transformer architectures, culminating in an overview of advanced topics in research (Website).