Self-supervised learning method and device based on motion sequence regression

Abstract

The invention discloses a self-supervised learning method and device based on motion sequence regression. The method comprises the following steps: S1, randomly intercepting video sample fragments with a fixed frame number; S2, calculating to obtain the average motion amount of the video sample segment; S3, randomly disordering the sequence of the inner frames of the video sample fragments to obtain disordered video sample fragments; S4, performing sequential judgment on the out-of-order video sample fragments; S5, synthesizing the average motion amount of the video sample fragments obtained in the step S2 and the sequential evaluation result obtained in the step S4 to generate a final sequential score for the out-of-order video sample fragments, and taking the final sequential score as aregression target value. According to the method and the system, the information of motion sequence consistency in the video is fully utilized, and the sequential score is automatically judged by randomly generating the samples and the intra-frame sequence of the samples and establishing a sequential judgment standard, so that the purpose of automatic labeling is achieved.

Description

technical field [0001] The invention relates to the technical field of image recognition, in particular to a self-supervised learning method and device based on motion sequential regression. Background technique [0002] In recent years, technologies based on deep learning (Deep Learning) have achieved good results in the field of computer vision, such as face recognition and target classification. Representative deep learning methods include CNN (convolutional neural network), RNN (recurrent neural network), GAN (generative confrontation network), etc. The emergence of deep learning technology has greatly improved the accuracy of traditional recognition algorithms, but its dependence on the number of labeled samples has also increased significantly. In order to obtain an ideal model training effect, it is often necessary to provide a large amount of labeled data as training samples. Therefore, the demand for labeled samples is growing rapidly. [0003] However, sample lab...

AI Technical Summary

Problems solved by technology

There is still a lack of effective means of utilizing the time relationship

Images