Paper Review Calls 011 -- U-Net: Convolutional Networks for Biomedical Image Segmentation

U-Net: Convolutional Networks for Biomedical Image Segmentation Ronneberger et al, 15 Roll up everybody! Join Karol Zak for a review of this seminal paper on semantic segmentation. Semantic segmentation is a popular task in computer vision to assign each pixel in an image to a class in a supervised fashion. Karol is our top expert in semantic segmentation (in CSE) and has been involved in several fascinating projects using it! https://arxiv.org/pdf/1505.04597.pdf "Abstract. There is large consent that successful training of deep networks requires many thousand annotated training samples. In this paper, we present a network and training strategy that relies on the strong use of data augmentation to use the available annotated samples more efficiently. The architecture consists of a contracting path to capture context and a symmetric expanding path that enables precise localization. We show that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks. Using the same network trained on transmitted light microscopy images (phase contrast and DIC) we won the ISBI cell tracking challenge 2015 in these categories by a large margin. Moreover, the network is fast. Segmentation of a 512x512 image takes less than a second on a recent GPU. The full implementation (based on Caffe) and the trained networks are available at http://lmb.informatik.uni-freiburg.de/people/ronneber/u-net ." https://www.linkedin.com/in/zakkarol/ Karol Zak Machine Learning Software Engineer at Microsoft "ML Engineer building and deploying machine learning models in cloud environment https://github.com/karolzak" COMPLIANCE NOTICE: * THIS WAS FILMED WHILE I WORKED AT MICROSOFT, NOW I DON'T * EVERYONE IN THIS VIDEO HAS GIVEN PERMISSION TO APPEAR IN THE VIDEO * NO MICROSOFT CONFIDENTIAL INFORMATION WAS DISCUSSED * WE ARE DISCUSSING PUBLIC LITERATURE * THESE ARE OUR PERSONAL OPINIONS * I REFERRED TO THE CHANNEL AS "MACHINE LEARNING AT MICROSOFT", IT HAS NOW BEEN RENAMED "MACHINE LEARNING DOJO" TO MAKE IT CLEAR IT'S NOT AN OFFICIAL MICROSOFT CHANNEL * THIS WAS FILMED IN APRIL 2019 IN OUR PERSONAL TIME