In our lab, we are working on model-based deep learning, where the design of learning-based algorithms is based on prior domain knowledge. This approach allows to integrate models and other knowledge about the problem into both the architecture and training process of deep networks. This leads to efficient, high-performance and yet interpretable neural networks which can be employed in a variety of tasks in signal and image processing. Model-based networks require far fewer parameters than their black-box counterparts, generalize better, and can be trained from much less data. In some cases, our networks are trained on a single image, or only on the input itself so that effectively they are unsupervised.
Turning iterations into layers. Connection to Implicit NNs.
- Jonas Adler, Learning to reconstruct
- Jonas Adler, Accelerated Forward-Backward Optimization using Deep Learning