Cross-domain target detection method based on multi-layer feature alignment

Abstract

The invention discloses a cross-domain target detection method based on multilayer feature alignment. The method includes: training a detector on a source domain data set with a frame label through adeep convolutional neural network; then, taking the trained detector as a pre-training model, and carrying out feature extraction on the pictures of the source domain and the target domain without theframe label through a deep convolutional neural network VGG-16 to enable the source domain and the target domain to share feature parameters; secondly, designing a domain classifier, taking the extracted feature layers of the multi-layer source domain and the target domain as the input of the domain classifier, and judging whether the feature layers are from the source domain or the target domain; and aligning the feature distribution of the source domain and the feature distribution of the target domain through the training mode of the generative adversarial network, so as to reduce the datadeviation between the two domains; and finally, carrying out joint training on the detector and the discriminator to obtain a final model. According to the invention, the knowledge of the source domain is migrated to the target domain, and the detection precision of the target domain data without frame annotation is improved.

Description

technical field [0001] The invention relates to the field of computer vision, in particular to a cross-domain target detection method based on multi-layer feature alignment. [0002] technical background [0003] In recent years, with the development of deep neural networks, significant progress has been made in data-driven computer vision. As a basic task of computer vision, target detection has attracted extensive attention from researchers, and it plays more and more roles in people's intelligent life. For example, in smart driving, 3D target detection can be used to quickly locate passing vehicles and surrounding scenes, so that cars can avoid obstacles and drive smoothly; Commodities, realize unmanned sales and save labor; in the smart community, through the license plate detection, passing vehicles can be quickly identified, so as to realize automatic release. All in all, target detection is increasingly becoming an indispensable part of our lives. [0004] Although ...

AI Technical Summary

Problems solved by technology

Although these detection methods based on full supervision have achieved good results, they are too dependent on a large amount of data and cannot effectively use the existing large amount of data.

However, data collection and labeling require a lot of manpower and material resources.

Images