Title:
METHOD AND APPARATUS FOR COMPUTER VISION
Document Type and Number:
WIPO Patent Application WO/2020/000171
Kind Code:
A1
Abstract:
Method and apparatus are disclosed for computer vision. The method may comprise processing, by using a neural network, input feature maps of an image to obtain output feature maps of the image. The neural network may comprise a convolution part and/or a pooling part, and an aggregation part. The convolution part may comprise at least one parallel unit each of which contains two parallel paths, each path of the two parallel paths contains two cascaded convolution layers. The kernel sizes are 1 dimension and are different in different unit. The pooling part comprises at least one parallel unit each of which contains two parallel paths, each path of the two parallel paths contains two cascaded pooling layers. The size of filters of pooling is 1 dimension and is different in different unit. The aggregation part is configured to concatenate results of the convolution part and/or the pooling part to obtain the output feature maps of the image.
Inventors:
LIAN XUHANG (CN)
Application Number:
PCT/CN2018/092809
Publication Date:
January 02, 2020
Filing Date:
June 26, 2018
Export Citation:
Assignee:
NOKIA TECHNOLOGIES OY (FI)
NOKIA TECH BEIJING CO LTD (CN)
NOKIA TECH BEIJING CO LTD (CN)
International Classes:
G06V10/764
Foreign References:
| US20170259801A1 | 2017-09-14 | |||
| CN105938559A | 2016-09-14 | |||
| CN107643826A | 2018-01-30 | |||
| CN107748895A | 2018-03-02 | |||
| US20180060719A1 | 2018-03-01 |
Other References:
L. C. CHENG. PAPANDREOUI. KOKKINOSK. MURPHYA. L. YUILLE: "DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs", IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2018
See also references of EP 3814981A4
See also references of EP 3814981A4
Attorney, Agent or Firm:
ZHONGZI LAW OFFICE (CN)
Download PDF: