Research on Open Set Recognition Based on Independent Classification Network
[Purpose]In order to solve the problem of image classification models lacking open set generaliza-tion due to traditional closed set training methods when facing open set recognition problems,we propose a sepa-rate independent classification network structure.[Method]Each category contains an independent linear fea-ture layer.The neural nodes designed in the feature layer can capture the category features more accurately under limited data samples.At the same time,a class of negative samples without labeling is introduced in the model training,so that the model not only relies on the feature difference of the known categories when constructing the decision boundary,but also increases the open set generalization of the model decision boundary without add-ing additional labeled samples.[Result]The results show that both the ICOR model structure and the open-set adaptive training strategy can effectively improve the OSR performance of traditional models;with the in-crease of openness,it can demonstrate better robustness;can more effectively reduce the OSR risk of the model.[Conclusion]The proposed independent classification network combined with open-set adaptive training algo-rithm has better open-set recognition performance than existing open-set recognition algorithms.
deep learningopen set recognitionimage classificationtransfer learning
国家科技期刊平台
NSTL
万方数据
