Block-Seminar on Deep Learning for Bio-Medical Image Analysisapl. Prof. Olaf Ronneberger (Google DeepMind)
In this seminar you will learn about relevant bio-medical research fields and the most recent methods (mainly based on deep learning) that have been already applied to bio-medical data, or that have a large potential in this field. For each paper there will be one person, who performs a detailed investigation of a research paper and its background and will give a presentation. The presentation is followed by a discussion with all participants about the merits and limitations of the respective paper. You will learn to read and understand contemporary research papers, to give a good oral presentation, to ask questions, and to openly discuss a research problem.
Papers (please note that we only have 10 places):
|Adversarial Networks for the Detection of Aggressive Prostate Cancer
Nice idea to train a segmentation model when there are multiple contradicting ground truth segmentations.
|Fully Convolutional Instance-aware Semantic Segmentation
Straight forward approach to tackle instance segmentation problem. New top scores on MS COCO.
|Unsupervised domain adaptation in brain lesion segmentation with adversarial networks
Domain adaption with unlabelled data -- unlabelled data is easy to obtain in the medical field. Labels are always expensive.
|Pixelwise Instance Segmentation with a Dynamically Instantiated Network
Another instance segmentation approach. Shows failure cases of FCIS.
|Optimization as a model for few-shot learning
Nice approach for few-shot learning. Limited training data sets is one of the main problems in the for biomedical domain.
|Learning Deep Nearest Neighbor Representations Using Differentiable Boundary Trees
Interpretability of network decisions is a hot topic in the medical field.
|Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles
As the title says.