Low-rank constraint online self-supervised learning scene classification method

Abstract

The invention relates to a low-rank constraint online self-supervised learning scene classification method. The method comprises the following steps: performing training and feature extraction on off-line image data; carrying out small-batch training to obtain an initial metric learner; inputting online data images sequentially and extracting image features; judging whether each image feature has a label; if the image feature has the label, updating the metric learner; if the image feature has no label, measuring the similarity between the image feature and each training sample, and utilizing a generated bidirectional linear graph to transmit the label; judging feature vector similarity scores of the sample; if the scores are high, updating the metric learner; and otherwise, inputting online data images. According to the scene classification method, self-updating can be realized gradually and useful information obtained from marked samples and unmarked samples can be combined; and the framework of a unified on-line self-updating model is utilized to process online scene classification, so that the on-line automatic scene classification can be achieved, the accuracy of classification is ensured, and work efficiency is improved.

Description

technical field [0001] The invention relates to an automatic scene classification method, in particular to a scene classification method through low-rank constraint online self-supervised learning. Background technique [0002] In today's society, machine learning techniques play a central role in many practical systems with visual cognition capabilities. Traditionally, machine learning models are trained offline from labeled training data that is constant throughout an online program, such as a machine vision system for scene classification in our example. Unfortunately, for practical online vision systems, the performance of the model may deteriorate over time and the new data may be very different from the initial training data. In order to deal with these problems, the model must be trained offline again in batch mode from existing data and new data, which will be time-consuming. More seriously, if the size of the dataset is too large, it will be difficult for the batc...

AI Technical Summary

Problems solved by technology

However, in practice data will always contain noise, so a high-rank metric matrix will cause overfitting and thus make the metric matrix susceptible to noise and interference

Images