NVIDIA Corporation
Label Generation Using Neural Networks

Last updated:

Abstract:

Apparatuses, systems, and techniques to train one or more neural networks to generate labels for unsupervised or partially-supervised data. In at least one embodiment, one or more pseudolabels are generated by a training framework based on available weak annotations for an input medical image, and combined with feature information about said input medical image generated by one or more neural networks to generate a label about said input medical image.

Status:
Application
Type:

Utility

Filling date:

27 Jul 2020

Issue date:

27 Jan 2022