Multi-task network model training method and system based on adaptive task weight

A network model and training method technology, applied in the field of computer vision, can solve problems such as inflexibility, disparity in learning effects, and difficulty in meeting actual needs, and achieve the effect of overcoming inflexibility and improving model performance.

Pending Publication Date: 2022-07-29
HANGZHOU DIANZI UNIV
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] There are two serious problems in the current multi-task learning research: (1) Most of the existing multi-task learning methods use hard parameter sharing and soft parameter sharing mechanisms to achieve feature sharing. In these two mechanisms, The model of each task is fixed. However, in social life, there are various tasks, and of course different sharing models are required. It is difficult to meet the actua

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Multi-task network model training method and system based on adaptive task weight
  • Multi-task network model training method and system based on adaptive task weight
  • Multi-task network model training method and system based on adaptive task weight

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0061] The present invention will be further described below with reference to the accompanying drawings.

[0062] The method of the present invention is suitable for two task classification scenarios of image semantic segmentation and surface normal estimation, which are specifically:

[0063] 1. Select the dataset and perform preprocessing

[0064] NYU v2 is a dataset composed of RGB images of indoor scenes, in which there are 40 categories of semantic segmentation, such as beds, cabinets, clothes, books, etc. After using the standard training / validation segmentation, the training set has 795 images, and the validation set has 654 images. In addition, this dataset has pixel-level surface normal ground truth precomputed by depth markers.

[0065] 2. Build a multi-task model

[0066] The multi-task network model includes network models of multiple tasks; the network model of each task includes the ResNet backbone network and a specific task layer;

[0067] This model selec...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention relates to a multi-task network model training method and system based on adaptive task weights. According to the method, a sharing mode is learned through a strategy specific to tasks, the strategy autonomously selects which layers are executed in a multi-task network, and weights matched with the tasks can be searched at the same time, so that the model is better trained. According to the method, the multi-task network model is reconstructed based on ResNet, the learning strategy is effectively optimized according to the image in the data set in the training process, and the oneness of the multi-task model is overcome while the task index is improved. According to the method, a multi-task loss function suitable for regression and classification tasks is deduced based on probability theory maximum likelihood estimation, the task weight can be automatically adjusted in the training process so as to better improve the model performance, and the problem that the task weight is not flexible is solved.

Description

technical field [0001] The invention belongs to the technical field of computer vision, and in particular relates to a multi-task network model training method and system based on adaptive task weights. Background technique [0002] The task of scene understanding is an important problem in the field of computer vision, involving the joint learning of various regression and classification tasks at different units and scales, including semantic labels that describe the identities of different scene parts and surface normals that describe the physical geometry. These are often represented as pixmaps, which contain values ​​or labels for each pixel, such as a map containing the semantic labels of objects at each pixel or the vector coordinates of surface normals. [0003] Multi-task learning (MTL) is a method of learning multiple tasks at the same time. It can use the shared knowledge learned from each task to help other tasks learn. Compared with single-task learning, it is mo...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06N3/04G06N3/08G06V10/764G06V10/766G06V10/26G06V10/82G06K9/62G06F9/48G06T7/66
CPCG06N3/084G06T7/66G06F9/4843G06N3/047G06N3/045G06F18/2415
Inventor 张传刚杨冰那巍
Owner HANGZHOU DIANZI UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products