Search International and National Patent Collections

1. (WO2018035805) COUPLED MULTI-TASK FULLY CONVOLUTIONAL NETWORKS USING MULTI-SCALE CONTEXTUAL INFORMATION AND HIERARCHICAL HYPER-FEATURES FOR SEMANTIC IMAGE SEGMENTATION

Pub. No.:    WO/2018/035805    International Application No.:    PCT/CN2016/096707
Publication Date: Fri Mar 02 00:59:59 CET 2018 International Filing Date: Fri Aug 26 01:59:59 CEST 2016
IPC: G06K 9/62
Applicants: INTEL CORPORATION
WANG, Libin
YAO, Anbang
CHEN, Yurong
Inventors: WANG, Libin
YAO, Anbang
CHEN, Yurong
Title: COUPLED MULTI-TASK FULLY CONVOLUTIONAL NETWORKS USING MULTI-SCALE CONTEXTUAL INFORMATION AND HIERARCHICAL HYPER-FEATURES FOR SEMANTIC IMAGE SEGMENTATION
Abstract:
Techniques related to implementing fully convolutional networks for semantic image segmentation are discussed. Such techniques may include combining feature maps from multiple stages of a multi-stage fully convolutional network to generate a hyper-feature corresponding to an input image, up-sampling the hyper-feature and summing it with a feature map of a previous stage to provide a final set of features, and classifying the final set of features to provide semantic image segmentation of the input image.