Image assessment using deep convolutional neural networks
Deep convolutional neural networks receive local and global representations of images as
inputs and learn the best representation for a particular feature through multiple …
inputs and learn the best representation for a particular feature through multiple …
Deep image-to-image network learning for medical image analysis
(57) ABSTRACT A method and apparatus for automatically performing medi cal image
analysis tasks using deep image-to-image network (DI2IN) learning. An input medical image …
analysis tasks using deep image-to-image network (DI2IN) learning. An input medical image …
Adversarial and dual inverse deep learning networks for medical image analysis
Methods and apparatus for automated medical image analysis using deep learning
networks are disclosed. In a method of automatically performing a medical image analysis …
networks are disclosed. In a method of automatically performing a medical image analysis …
Systems and methods for correcting error in a first classifier by evaluating classifier output in parallel
AS Heifets, I Wallach, KT Nguyen - US Patent 10,546,237, 2020 - Google Patents
Systems and methods for classifying a test object are pro vided. For each respective target
object in a plurality of target objects, a first procedure is performed comprising (a) posing the …
object in a plurality of target objects, a first procedure is performed comprising (a) posing the …
Accelerating convolutional neural network computation throughput
PK Balasubramanian - US Patent 10,482,337, 2019 - Google Patents
Convolutional neural network (CNN) components can operate to provide various speed-ups
to improve upon or operate as part of an artificial neural network (ANN). A convolution …
to improve upon or operate as part of an artificial neural network (ANN). A convolution …
Object recognition method and apparatus based on weakly supervised learning
Provided are an object recognition method and apparatus which determine an object of
interest included in a recognition target image using a trained machine learning model and …
interest included in a recognition target image using a trained machine learning model and …
Optimized neural network input stride method and apparatus
JW Brothers - US Patent 10,776,694, 2020 - Google Patents
A convolutional layer in a convolutional neural network uses a predetermined horizontal
input stride and a predetermined vertical input stride that are greater than 1 while the …
input stride and a predetermined vertical input stride that are greater than 1 while the …
Learning image categorization using related attributes
A first set of attributes (eg, style) is generated through pre-trained single column neural
networks and leveraged to regularize the training process of a regularized double-column …
networks and leveraged to regularize the training process of a regularized double-column …
Cross-domain image analysis and cross-domain image synthesis using deep image-to-image networks and adversarial networks
Methods and apparatus for cross-domain medical image analysis and cross-domain
medical image synthesis using deep image-to-image networks and adversarial networks are …
medical image synthesis using deep image-to-image networks and adversarial networks are …
Surface defect detection
A method is provided of forming a neural network for detecting surface defects in aircraft
engine components. The method includes: providing (i) a pre-trained deep learning network …
engine components. The method includes: providing (i) a pre-trained deep learning network …