Unlock instant, AI-driven research and patent intelligence for your innovation.

Image classification method, and training method and device of image classification model

A classification method and classification model technology, applied in the field of artificial intelligence, can solve problems such as poor adaptability, and achieve the effects of enhancing adaptability, increasing image throughput, and reducing the number of local vectors

Pending Publication Date: 2022-04-29
TENCENT TECH (SHENZHEN) CO LTD
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Moreover, DynamicViT can only be applied to the ViT model with fixed image resolution input. Once the resolution of the input image is determined, it cannot be changed, and the adaptability is poor.

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
  • Image classification method, and training method and device of image classification model
  • Image classification method, and training method and device of image classification model
  • Image classification method, and training method and device of image classification model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0088] Embodiments of the present application are described below with reference to the drawings in the present application. It should be understood that the implementation manner described below in conjunction with the accompanying drawings is an exemplary description for explaining the technical solutions of the embodiments of the present application, and does not limit the technical solutions of the embodiments of the present application.

[0089] Those skilled in the art will understand that unless otherwise stated, the singular forms "a", "an", "" and "the" used herein may also include plural forms. It should be further understood that the terms "comprising" and "comprising" used in the embodiments of the present application mean that the corresponding features can be implemented as the presented features, information, data, steps, operations, elements and / or components, but do not exclude The realization is other features, information, data, steps, operations, elements, ...

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 embodiment of the invention provides an image classification method and an image classification model training method and device, and relates to the field of artificial intelligence. The method comprises the steps that an image to be classified is input into a coding layer of a pre-trained image classification model, vector extraction is carried out, a feature vector is obtained, the feature vector comprises a plurality of local vectors, and each local vector corresponds to a sub-image in the image to be classified; screening the local vectors by using an attention mechanism layer in the coding layer to obtain residual local vectors; and obtaining a classification result of the to-be-classified image based on the residual local vectors. According to the embodiment of the invention, in the process of reducing the local vector, an auxiliary network is not needed, more parameters are not introduced, and a lightweight image classification model can be trained from the beginning, so that the calculation amount can be reduced, the method is also suitable for images with different resolutions, and the adaptability of the scheme is enhanced.

Description

technical field [0001] The present application relates to the technical field of artificial intelligence, and in particular, the present application relates to an image classification method, a training method and a device for an image classification model. Background technique [0002] Computations in deep learning models are often redundant. In order to deploy deep neural networks on mobile devices, the memory and computational overhead of neural networks must be reduced. [0003] There are some methods in the related art to reduce the computational burden of the deep neural network. For example, DynamicViT (Vision Transformer) proposed by Rao et al., which introduces a method to reduce the number of tokens of ViT that has been trained. Specifically, DynamicViT adds an additional learnable neural network to ViT to select a subset of input tokens and discard unselected tokens, thereby reducing the amount of computation. [0004] DynamicViT needs a well-trained ViT to ini...

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): G06K9/62G06N3/04G06N3/08G06V10/764G06V10/774G06V10/82
CPCG06N3/084G06N3/045G06F18/241G06F18/214
Inventor 宋奕兵梁有为
Owner TENCENT TECH (SHENZHEN) CO LTD