Computer Vision has long been an important driving force for advances in ML, and have been instrumental in the rise and development of deep learning. The module will start with convolutional neural networks for image classification, and extensions like dropout, batch normalisation, data augmentation, transfer learning, and visual attention. Other typical Computer Vision tasks will then be overviewed, including object segmentation, colourisation, style transfer, and automated image captioning. Finally generative models for Computer Vision, including variational autoencoders and generative adversarial networks, will be covered.
Upon completion of the module the student will be able to:
- summarise, implement and critically assess basic and state-of-the-art deep learning approaches to solve a variety of Computer Vision problems;
- formulate and interpret the mathematical theory underlying common Computer Vision approaches;
- apply a number of devices necessary to build practical solutions to Computer Vision problems;
- discuss problems and approaches at the cutting edge of Computer Vision research, from an ML and AI perspective.