We will introduce several computer vision problems, ranging from object classification and localization to semantic segmentation and video analysis. The fundamentals of the classical approaches to these problems will be covered, but the main focus will be on deep learning algorithms—especially convolutional neural networks—that are used to hierarchically extract increasingly more abstract features from images, analogous to processes performed by the human visual system.
- Trainer/in: Muhammad Ahsan
- Trainer/in: Kshitij Dwivedi
- Trainer/in: Matthias Fulde
- Trainer/in: Gemma Roig