Background motion estimation in motion photos. By using the motion metadata from Gyro and OIS we are able to accurately classify features from the visual analysis into foreground and background.
Source: googleblog.com
SNNs are really cool: their goal is to create neural networks in which, if the input of any layer is normally distributed, the output will automatically also be normally distributed. This is amazing because normalizing the output of layers is known to be a very efficient way to improve the performance of neural networks, but the current ways to do it (eg BatchNorm) basically involve weird hacks, while in SNN the normalization is an intrinsic part of the mathematics of the neural net.
Read More
Today, we are excited to announce the open source release of our latest and best performing semantic image segmentation model, DeepLab-v3+ [1], implemented in Tensorflow. This release includes DeepLab-v3+ models built on top of a powerful convolutional neural network (CNN) backbone architecture [2, 3] for the most accurate results, intended for server-side deployment. As part of this release, we are additionally sharing our Tensorflow model training and evaluation code, as well as models already pre-trained on the Pascal VOC 2012 and Cityscapes benchmark semantic segmentation tasks.
Read More
Interpretability techniques are normally studied in isolation. We explore the powerful interfaces that arise when you combine them — and the rich structure of this combinatorial space.
Read More