US 11,836,632 B2
Method and system for image classification
Shudong Xie, Singapore (SG); Yiqun Li, Singapore (SG); Dongyun Lin, Singapore (SG); Tin Lay Nwe Ma, Singapore (SG); and Sheng Dong, Singapore (SG)
Assigned to Agency for Science, Technology and Research, Singapore (SG)
Appl. No. 17/598,135
Filed by Agency for Science, Technology and Research, Singapore (SG)
PCT Filed Mar. 26, 2020, PCT No. PCT/SG2020/050169
§ 371(c)(1), (2) Date Sep. 24, 2021,
PCT Pub. No. WO2020/197501, PCT Pub. Date Oct. 1, 2020.
Claims priority of application No. 10201902708Y (SG), filed on Mar. 26, 2019.
Prior Publication US 2022/0189143 A1, Jun. 16, 2022
Int. Cl. G06V 10/764 (2022.01); G06V 10/77 (2022.01); G06V 10/774 (2022.01); G06V 10/82 (2022.01); G06N 3/084 (2023.01)
CPC G06N 3/084 (2013.01) [G06V 10/765 (2022.01); G06V 10/7715 (2022.01); G06V 10/7747 (2022.01); G06V 10/82 (2022.01)] 18 Claims
OG exemplary drawing
 
1. A computer-implemented method of image classification using at least one processor, the method comprising:
providing a set of category mapping discriminators, each corresponding to a respective category, wherein each category mapping discriminator of the set of category mapping discriminators is configured for discriminating features relating to input images that belong to the respective category of the category mapping discriminator;
extracting a plurality of features from an input image using a machine learning model;
determining, for each of the set of category mapping discriminators, an output value based on the plurality of extracted features using the category mapping discriminator; and
determining a classification of the input image based on the output values of the set of category mapping discriminators,
wherein said providing a set of category mapping discriminators further comprises generating one or more new category mapping discriminators corresponding to one or more new categories, respectively, each new category mapping discriminator is configured for discriminating features relating to input images that belong to the respective new category of the new category mapping discriminator, and incorporating the one or more new category mapping discriminators into the set of category mapping discriminators to obtain an updated set of category mapping discriminators.