US 11,727,676 B2
Feature fusion method and apparatus for image processing, electronic device and storage medium
Yingying Li, Beijing (CN); Xiao Tan, Beijing (CN); Minyue Jiang, Beijing (CN); and Hao Sun, Beijing (CN)
Assigned to BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD., Beijing (CN)
Filed by BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD., Beijing (CN)
Filed on Mar. 26, 2021, as Appl. No. 17/213,746.
Claims priority of application No. 202010309211.9 (CN), filed on Apr. 17, 2020.
Prior Publication US 2021/0232856 A1, Jul. 29, 2021
Int. Cl. G06V 10/82 (2022.01); G06T 3/00 (2006.01); G06V 10/77 (2022.01); G06V 10/80 (2022.01); G06F 18/213 (2023.01); G06F 18/211 (2023.01); G06F 18/25 (2023.01)
CPC G06V 10/82 (2022.01) [G06F 18/211 (2023.01); G06F 18/213 (2023.01); G06F 18/253 (2023.01); G06T 3/00 (2013.01); G06V 10/7715 (2022.01); G06V 10/806 (2022.01)] 12 Claims
OG exemplary drawing
 
1. An image processing method, comprising:
inputting an image into a feature extraction model to generate N dimensional features, N being a positive integer, and the N dimensional features being N features each corresponding to one of multiple dimensions;
performing dimension fusion on M features selected from the N dimensional features to obtain M dimension fusion features, M being a positive integer and less than or equal to N; and
processing the image based on M dimension fusion features and remaining features of the N dimensional features other than the M features,
wherein performing the dimension fusion on the M features selected from the N dimensional features to obtain the M dimension fusion features comprises:
selecting the M features from the N dimensional features based on the number of dimensions corresponding to the N dimensional features;
generating M dimensional features by transforming the M features from a feature map space to a dimension space; and
convoluting and fusing the M dimensional features to obtain the M dimension fusion features.