Semantic Preserving Models and Unsupervised Microvascular Segmentation

Agenda:
18:00-18:15 - Networking
18:15-19:00 - Semantic Preserving Generative Adversarial Models by Amir Ronen
19:00-19:45 - Unsupervised Microvascular Image Segmentation Using an Active Contours Mimicking Neural Network by Shir Gur

Semantic Preserving Generative Adversarial Models by Amir Ronen

We introduce generative adversarial models in which the discriminator is replaced by a calibrated (non-differentiable) classifier repeatedly enhanced by domain relevant features. The role of the classifier is to prove that the actual and generated data differ over a controlled semantic space. We demonstrate that such models have the ability to generate objects with strong guarantees on their properties in a wide range of domains. They require less data than ordinary GANs, provide natural stopping conditions, uncover important properties of the data, and enhance transfer learning. Our techniques can be combined with standard generative models. We demonstrate the usefulness of our approach by applying it to several unrelated domains: generating good locations for cellular antennae, molecule generation preserving key chemical properties, and generating and extrapolating lines from very few data points. Intriguing open problems are presented as well. Joint work with Shahar Harel and Meir Maor
Amir Ronen is the Chief Scientist of Spark Beyond. His main interests lie on the border of machine learning and algorithms. He is often fascinated by deep mathematical ideas that have far reaching practical implications. Amir was a postdoctoral research fellow at Stanford University and UC Berkeley, a faculty member at the Technion, and a researcher at IBM. He received various awards including the Gödel prize, the Best Paper Prize from the International Joint Conferences Artificial Intelligence (IJCAI) and the Journal of Artificial Intelligence Research (JAIR), and the Wolf prize for Ph.D. Students.

Unsupervised Microvascular Image Segmentation Using an Active Contours Mimicking Neural Network

We present a novel deep learning method for unsupervised segmentation of blood vessels. The method is inspired by the field of active contours and we introduce a new loss term, which is based on the morphological Active Contours Without Edges (ACWE) optimization method. The role of the morphological operators is played by novel pooling layers that are incorporated to the network’s architecture. We demonstrate the challenges that are faced by previous supervised learning solutions, when the imaging conditions shift. Our unsupervised method is able to outperform such previous methods in both the labeled dataset, and when applied to similar but different datasets.

Shir Gur is a Ph.D. student at the Computer Science Department at Tel-Aviv University, working with Prof. Lior Wolf. Before, he was M.Sc. student working with Prof. Ohad Ben-Shahar at Ben-Gurion University of the Negev. His research interests include Machine Learning, specifically Deep Learning, solving unsupervised problems in Computer vision.