Title:
IMAGE CLASSIFICATION LEARNING DEVICE, IMAGE CLASSIFICATION LEARNING METHOD, IMAGE CLASSIFICATION LEARNING PROGRAM, AND POST-IMAGE-CLASSIFICATION LEARNING MODEL
Document Type and Number:
WIPO Patent Application WO/2024/085114
Kind Code:
A1
Abstract:
The present invention provides an image classification learning device that makes it possible to learn a "concept" to be used by a post-learning model to make a determination. A concept learner 200 performs machine learning of a plurality of concepts in image data on the basis of learning data including the image data and an image label. A concept prototype processing unit 2100 is an attention mechanism that, in a concept matrix comprising slot vectors, converts the slot vectors according to image features defined in the slot vectors, the slot vectors respectively corresponding to a plurality of concepts and defining an image region in which feature quantities emphasized in identification processing by an image identification means appear. A learning processing control unit 700 controls learning processing so as to decrease a loss calculated on the basis of: an identification loss that decreases as the identification rate of a classifier 400 increases, and a separation loss that decreases as the degree of mutual separation of the feature quantities corresponding to the plurality of concepts in a feature quantity space increases.
More Like This:
Inventors:
TSURUTA SHUICHI (JP)
NAKASHIMA YUTA (JP)
LI LIANGZHI (JP)
WANG BOWEN (JP)
NAKASHIMA YUTA (JP)
LI LIANGZHI (JP)
WANG BOWEN (JP)
Application Number:
PCT/JP2023/037394
Publication Date:
April 25, 2024
Filing Date:
October 16, 2023
Export Citation:
Assignee:
UNIV OSAKA (JP)
International Classes:
G06V10/764; G06T7/00; G06V10/77; G06V10/82
Attorney, Agent or Firm:
SHOBAYASHI Masayuki et al. (JP)
Download PDF: