Deep transfer learning method and device, electronic equipment and storage medium

Abstract

The invention provides a deep transfer learning method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a source domain data set with a category label, dividing the source domain data set into a plurality of sub-source domain data sets, and carrying out the training of each sub-source domain data set to obtain a corresponding candidate pre-training model; obtaining a target domain data set with category labels, and calculating the similarity between the target domain data set and each sub-source domain data set; according to the similarity between the target domain data set and each sub-source domain data set, selecting a target pre-training model from the candidate pre-training models; and performing fine adjustment on the target pre-training model by using the target domain data set to obtain an optimal classification model of the target domain data set. According to the embodiment of the invention, the condition of negative migration in the transfer learning process is avoided, so that the transfer learning effect is improved.

Description

technical field [0001] The present application relates to the technical field of computer vision, and in particular to a deep transfer learning method, device, electronic equipment and storage medium. Background technique [0002] Computer vision is a science that studies how to make machines "see" and "process". Its goal is to enable machines to observe and understand the world through vision like humans, and have the ability to adapt to the environment autonomously. In the field of computer vision, transfer learning is a widely used technology, which can transfer the knowledge learned in one field to another, so as to speed up model training and improve model prediction accuracy. The current transfer learning is based on a large-scale general dataset training model. The general dataset can be the face image data collected at the gate channel, or the face image data obtained from the open source database, or it can also be the face image data collected on the highway. Capt...

AI Technical Summary

Problems solved by technology

The current transfer learning is based on a large-scale general dataset training model. The general dataset can be the face image data collected at the gate channel, or the face image data obtained from the open source database, or it can also be the face image data collected on the highway. Captured vehicle image data, etc., and then fine-tuned the trained model. However, large-scale general-purpose data sets are prone to negative transfer in the process of migrating to the target domain, and the effect of transfer learning is not significant.

Images