Training model and small sample classification method and device

Abstract

The invention discloses a training model and small sample classification method and device, the similarity of local features between different samples is calculated, the subsequently determined weightdistribution can better reflect the importance degree of symbiotic information between the samples, and when an optimal transmission problem is constructed, the optimal transmission problem is solvedby adding an entropy regularization item. Therefore, a transmission cost matrix can be obtained through iterative optimization, and finally, a loss function is determined based on the transmission cost matrix of each sample pair and the annotation of each query sample in the training sample set, so that the feature extraction model learns to extract more effective features for classifying the query samples. Therefore, the training model does not learn the transmission cost matrix used for weighting, but calculates each sample pair to obtain the transmission cost matrix, so that the embodimentprovided by the specification is not limited by the learned general weighting matrix, and can adapt to samples of different types of scenes.

Description

technical field [0001] This specification relates to the technical field of automatic driving, and in particular to a method and device for training models and classifying small samples. Background technique [0002] At present, supervised learning has become an important model training method, but when training a deep learning model, a large number of training samples are required to ensure the effect of model training. [0003] When there are few training samples but a deep learning model needs to be trained, it is necessary to train the deep model based on small samples. One of the methods is to classify the test samples in the test sample library based on small samples, which can also be regarded as the labeling of the test samples, so as to obtain a large number of samples for training the deep learning model. It can be seen that the accuracy of the test sample annotation determines the training effect of the deep learning model. [0004] In the prior art, small sampl...

AI Technical Summary

Problems solved by technology

[0006] However, the feature extraction model trained by the existing technology is usually a general model, that is, it is used for labeling samples in different scenarios, and there are differences in the similarity between samples in different scenarios, resulting in the labeling of samples obtained by existing training. The adaptability of the model is insufficient, and the accuracy of the labeling results is low, which affects the training effect of the subsequent deep learning model based on the labeled samples

Images