Long-tail distribution image data identification method based on dual-channel learning

Abstract

The invention discloses a long-tail distribution image data identification method based on dual-channel learning. The method comprises the following steps: 1) constructing a dual-channel learning model combining unbalanced learning and small sample learning; 2) updating all parameters in the dual-channel learning model by utilizing dual-channel learning total loss and back propagation, and storingoptimal dual-channel learning model parameters; and 3) inputting the image data of the test set to the optimal dual-channel learning model, and obtaining the prediction label of the image. Accordingto the invention, unbalanced learning and small sample learning are combined to solve the problem of long-tail distribution image data identification; the unbalanced learning channel can improve the identification accuracy of the unbalanced data set; the small sample learning channel can improve the feature representation of model learning, and the dual-channel total loss enables the model to focus on the unbalanced learning channel in the early stage of training and focus on the small sample learning channel in the later stage of training, thereby improving the recognition accuracy of the long-tail distribution image data on the whole.

Description

technical field [0001] The invention relates to the technical field of unbalanced classification, small-sample learning, and long-tail distribution image data recognition in machine learning, in particular to a long-tail distribution image data recognition method based on dual-channel learning. Background technique [0002] Long-tail distribution image data recognition usually uses technologies related to unbalanced learning, which are mainly divided into data level and algorithm level. Data-level techniques mainly include downsampling of majority class samples, upsampling of minority class samples or a hybrid sampling method combining the two. However, the resampled data cannot reflect the real data distribution characteristics. For example, the down-sampling method will discard most of the samples, thus losing a lot of valuable information in the data set. The up-sampling method will lead to over-fitting problems and bring Huge computing power consumption. The technology...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to overcome the shortcomings and deficiencies of the prior art, and proposes an effective, scientific and reasonable long-tail distribution image data recognition method based on dual-channel learning, which combines unbalanced learning and small sample learning for To solve the problem of long-tail distribution image data recognition, the unbalanced learning channel can improve the recognition accuracy of the model for unbalanced datasets, and the small-sample learning channel can improve the feature representation learned by the model and enhance the model's ability to recognize tail-like image data; The constructed dual-channel learning total loss function enables the model to focus on the unbalanced learning channel in the early stage of training, and focus on the small-sample learning channel in the later stage of training, thereby improving the recognition accuracy of the model for long-tail image data as a whole.

Images