Title:
ＣＮＮ学習方法及び学習装置、これを利用したテスト方法及びテスト装置
Document Type and Number:
Japanese Patent JP6857368
Kind Code:
B2
Abstract:
A method for learning parameters of a CNN for image recognition is provided to be used for hardware optimization which satisfies KPI. The method includes steps of: a learning device (a) instructing a first transposing layer or a pooling layer to generate an integrated feature map by concatenating pixels, per each ROI, on pooled ROI feature maps; (b) instructing a 1×H1 convolutional layer to generate a first adjusted feature map using a first reshaped feature map, generated by concatenating features in H1 channels of the integrated feature map, and instructing a 1×H2 convolutional layer to generate a second adjusted feature map using a second reshaped feature map, generated by concatenating features in H2 channels of the first adjusted feature map; and (c) instructing a second transposing layer or a classifying layer to divide the second adjusted feature map by each pixel, to thereby generate pixel-wise feature maps.
Inventors:
Kim, Kei-Hyun
Kim, Yong Jun
Kim, Insoo
Kim, haku-kyung
Nam, Woo Hyun
Boo, Soohun
Son, Munchur
Yeoh, Dong Hoon
Liu, Uju
Chang, Taeun
John, Kyun Chung
Choi, Hongo
Butterfly, hojin
Kim, Yong Jun
Kim, Insoo
Kim, haku-kyung
Nam, Woo Hyun
Boo, Soohun
Son, Munchur
Yeoh, Dong Hoon
Liu, Uju
Chang, Taeun
John, Kyun Chung
Choi, Hongo
Butterfly, hojin
Application Number:
JP2020001957A
Publication Date:
April 14, 2021
Filing Date:
January 09, 2020
Export Citation:
Assignee:
Stradvision,Inc.
International Classes:
G06T7/00; G06N3/04; G06T7/11; G06V10/82
Domestic Patent References:
| JP2018503152A |
Attorney, Agent or Firm:
Asamura patent office