Multi-field adaptive model training method, system and device and storage medium

Abstract

The invention provides a multi-domain adaptive model training method, system and device and a storage medium, and the method comprises the steps: obtaining source domain data and target domain data, dividing the target domain data into a plurality of groups according to different domains, and each group comprises the target domain data of one domain; the source domain data is input into a source domain classification network, a group of target domain data is input into a target domain classification network for training, the weight of an incremental convolutional layer is updated according to a training result, and the weights of the source domain classification network and the target domain classification network are shared; loading the weight of the incremental convolutional layer to a source domain classification network and a target domain classification network; and selecting another group of target domain data, and carrying out iterative training until the target domain data is trained, so as to obtain a multi-domain adaptive model. The problem that only a single source domain to a single target domain can be used in a traditional adaptive model is solved.

Description

technical field [0001] The present invention relates to the technical field of cross-domain models, in particular to a training method, system, device and storage medium for a multi-domain adaptive model. Background technique [0002] As an important basic task of computer vision, image classification has been widely used in the fields of unmanned driving, video monitoring, face recognition and so on. In recent years, image classification tasks based on deep learning have been widely discussed and studied. Such methods use a large number of publicly labeled samples to train convolutional neural networks with different structures to form image classification deep networks, and in the homologous dataset test, the classification accuracy rate is improved. Satisfactory results were obtained in terms of classification speed. It effectively reduces the incompleteness caused by artificially designed features, and reconciles the contradiction between the generality of features and ...

AI Technical Summary

Problems solved by technology

[0005] However, in the existing technology, the migration learning model only focuses on feature alignment during training, while ignoring the discriminative row features of samples after migration, and it is only used for cross-domain tasks of migrating from a single source domain to a single target domain, resulting in the model being unable to learn multiple Cross-domain task from source domain to multiple target domains

Images