Microsoft Technology Licensing, LLC

Wisconsin Alumni Research Foundation

Insurance Services Office, Inc.

Vishnu Sai Rao Suresh Lokhande

Maneesh Kumar Singh

Vikas Singh

Julian Yarkony

Vibhav Vineet

Ondrej Miksik

Tuan Dinh

Konrad Kording

Shaofei Wang

Sathya Narayanan Ravi

Computer vision systems and methods for end-to end training of neural networks are provided. The system generates a fixed point algorithm for dual-decomposition of a maximum-a-posteriori inference problem and trains the convolutional neural network and a conditional random field with the fixed point algorithm and a plurality of images of a dataset to learn to perform semantic image segmentation. The system can segment an attribute of an image of the dataset by the trained neural network and the conditional random field.

Computer vision systems and methods for end-to-end training of convolutional neural networks using differentiable dual-decomposition techniques

Embodiments of the present invention provide systems, methods, and computer storage media directed to optimizing the accuracy of local feature detection in a variety of physical environments. Homographic adaptation for facilitating personalization of local feature models to specific target environments is formulated in a bilevel optimization framework instead of relying on conventional randomization techniques. Models for extraction of local image features can be adapted according to homography transformations that are determined to be most relevant or optimal for a user's target environment.

Personalized local image features using bilevel optimization

An architecture for training the weights of artificial neural networks provides a global constrainer modifying the neuron weights in each iteration not only by the back-propagated error but also by a global constraint constraining these weights based on the value of all weights at that iteration. The ability to accommodate a global constraint is made practical by using a constrained gradient descent which approximates the error gradient deduced in the training as a plane, offsetting the increased complexity of the global constraint.

Training system for artificial neural networks having a global weight constrainer

Growing community of inventors

Madison, WI, United States of America

Vishnu Sai Rao Suresh Lokhande