Title:
METHOD AND APPARATUS FOR LEARNING DEEP LEARNING MODEL FOR ORDINAL CLASSIFICATION PROBLEM BY USING TRIPLET LOSS FUNCTION
Document Type and Number:
WIPO Patent Application WO/2019/231105
Kind Code:
A1
Abstract:
The present invention relates to image processing using machine learning, and a method for learning a deep learning model for an ordinal classification problem makes a learning object into an input; forms convolutional neural networks (CNNs) including a branch point and two end points, which are separated from a branch thereof so as to cause classification loss and triplet loss, calculates classification loss for end-to-end learning, calculates the triplet loss such that a network can learn ordinal characteristics, and updates the network for a final loss value by performing relative triplet sampling on the basis of the calculated classification loss and triplet loss, thereby enabling effective learning and loss control.
Inventors:
YANG HYUN-SEUNG (KR)
IM WOOBIN (KR)
HONG SUNGEUN (KR)
YOON SUNG-EUI (KR)
IM WOOBIN (KR)
HONG SUNGEUN (KR)
YOON SUNG-EUI (KR)
Application Number:
PCT/KR2019/004452
Publication Date:
December 05, 2019
Filing Date:
April 12, 2019
Export Citation:
Assignee:
KOREA ADVANCED INST SCI & TECH (KR)
International Classes:
G06N3/08; G06K9/62; G06N3/04
Domestic Patent References:
| WO2017203262A2 | 2017-11-30 |
Foreign References:
| US20170124711A1 | 2017-05-04 |
Other References:
LIU, HAO ET AL.: "Label-Sensitive Deep Metric Learning for Facial Age Estimation", IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECUCITY, vol. 13, no. 2, February 2018 (2018-02-01), pages 292 - 305, XP011673384, DOI: 10.1109/TIFS.2017.2746062
BAE, BYEONG-UK ET AL.: "Improved Deep Learning Model for Bone Age Assessment using Triplet Ranking Loss", OPEN REVIEW, 12 April 2018 (2018-04-12), pages 1 - 3, XP055659494
LIU. HAO ET AL.: "Ordinal Deep Feature Learning for Facial Age Estimation", 2017 IEEE 12TH INTERNATIONAL CONFERENCE AN AUTOMATIC FACE & GESTURE RECOGNITION, 29 June 2017 (2017-06-29), pages 157 - 164, XP033109700
BAE, BYEONG-UK ET AL.: "Improved Deep Learning Model for Bone Age Assessment using Triplet Ranking Loss", OPEN REVIEW, 12 April 2018 (2018-04-12), pages 1 - 3, XP055659494
LIU. HAO ET AL.: "Ordinal Deep Feature Learning for Facial Age Estimation", 2017 IEEE 12TH INTERNATIONAL CONFERENCE AN AUTOMATIC FACE & GESTURE RECOGNITION, 29 June 2017 (2017-06-29), pages 157 - 164, XP033109700
Attorney, Agent or Firm:
CHUNG HYUN PATENT & LAW FIRM (KR)
Download PDF:
Previous Patent: METHOD FOR CLASSIFYING IMAGES BY USING DEEP NEURAL NETWORK AND APPARATUS USING SAME
Next Patent: LENGTH-ADJUSTABLE BABY CARRIER
Next Patent: LENGTH-ADJUSTABLE BABY CARRIER