Computer Vision is an emerging technology with numerous applications. Since computers and GPUs became more powerful, neural networks could be applied to an increasing number of existing problems.
The goal of this seminar is to familiarize students with central challenges and state-of-the-art technologies in the area of computer vision and deep learning. Students will choose one topic out of:
- Architectures of Convolutional Neural Networks in Computer Vision
- 3D Model Datasets and their Applications in Computer Vision
- Classification and Analysis of Large Scale Image Datasets
- Generative AI in Computer Vision
- Evolution of the YOLO Model
- Optimization and Regularization Techniques for Deep Learning
Each student then gains expert knowledge on their topic by reading relevant literature, prepares a scientific survey and holds a presentation.
- Lehrende(r): Peter Roch
- Lehrende(r): Elke Schulte-Lippern
- Lehrende(r): Bijan Shahbaz Nejad