Trademark image retrieval model training method and system, storage medium and computer device

Abstract

The invention relates to a trademark image retrieval model training method, which comprises the following steps: obtaining a plurality of groups of sample data, and selecting a most difficult positiveexample sample and a plurality of difficult negative example samples for each query sample according to similarity; taking one query sample, the corresponding most difficult positive example sample and the plurality of corresponding difficult negative example samples as a group of training data, and performing trademark image retrieval model training by utilizing a neural network according to theplurality of groups of training data; and updating the trademark image retrieval model according to the multi-negative example comparison loss function until the verification effect of the trademarkimage retrieval model on the verification set is not improved any more, and ending the training. According to the method, easy samples are removed and difficult-to-divide samples are mined according to the similarity, a small number of difficult-to-divide samples are fully utilized, neural network parameters are adjusted in a more targeted mode, model convergence / over-fitting can be well delayed,training is more sufficient, and the effect is better. The invention further relates to a trademark image retrieval model training system, a storage medium and a computer device.

Description

technical field [0001] The invention relates to the technical field of model training, in particular to a trademark image retrieval model training method, system, storage medium and computer equipment. Background technique [0002] In the prior art, the training method of trademark image retrieval model generally adopts fixed or random positive and negative examples. Fixed positive and negative examples are likely to lead to model overfitting, that is, the effect is only good on the training data; random positive and negative examples are likely to lead to underfitting. Fitting and insufficient training, that is, most of the models seen are very simple cases, and there is no targeted training to improve error-prone cases. Contents of the invention [0003] The technical problem to be solved by the present invention is to provide a trademark image retrieval model training method, system, storage medium and computer equipment for the problems existing in the prior art. [0...

AI Technical Summary

Problems solved by technology

[0002] In the prior art, the training method of trademark image retrieval model generally adopts fixed or random positive and negative examples. Fixed positive and negative examples are likely to lead to model overfitting, that is, the effect is only good on the training data; random positive and negative examples are likely to lead to underfitting. Fitting and insufficient training, that is, most of the models seen are very simple cases, and there is no targeted training for error-prone cases to improve

Images