Title:
NEURAL NETWORK MODEL FOR IMAGE SEGMENTATION AND IMAGE SEGMENTATION METHOD THEREFOR
Document Type and Number:
WIPO Patent Application WO/2021/128896
Kind Code:
A1
Abstract:
A neural network model for image segmentation, an image segmentation method therefor and device thereof, and a readable storage medium. The model comprises an intelligent selection module, and the intelligent selection module further comprises a feature extraction unit and an intelligent selection unit. Since the feature extraction unit uses multi-scale dilated convolution to obtain information of different scales of an input feature map, a large quantity of diverse feature information is provided for later feature screening. In addition, the intelligent selection unit trains a weight value, and performs intelligent screening on an input feature map channel according to the size of the weight value. Therefore, the intelligent selection module can ensure segmentation accuracy while reducing the number of parameters and the amount of calculation. Therefore, by using the described intelligent selection module, the neural network model of the present application can quickly extract an effective feature of an image; moreover, the amount of calculation is small and model parameters are few, and the model is applicable to a mobile terminal.
Inventors:
WANG LI (CN)
GUO ZHENHUA (CN)
ZHAO YAQIAN (CN)
GUO ZHENHUA (CN)
ZHAO YAQIAN (CN)
Application Number:
PCT/CN2020/110983
Publication Date:
July 01, 2021
Filing Date:
August 25, 2020
Export Citation:
Assignee:
INSPUR ELECTRONIC INFORMATION INDUSTRY CO LTD (CN)
International Classes:
G06K9/34; G06K9/46; G06N3/04
Foreign References:
| CN111079767A | 2020-04-28 | |||
| CN110232394A | 2019-09-13 | |||
| CN110189337A | 2019-08-30 | |||
| CN106934397A | 2017-07-07 | |||
| CN110136141A | 2019-08-16 | |||
| CN110348411A | 2019-10-18 |
Other References:
See also references of EP 4053739A4
Attorney, Agent or Firm:
UNITALEN ATTORNEYS AT LAW (CN)
Download PDF: