Curriculum paradigm based on the dynamic weights of samples for semi-supervised learning
This work studies the difficulty of label propagation and serious noise interference in model training,which are due to the extreme lack of supervision signals in semi-supervised learning scenarios.Noise from pseudo-labeling and confirmation bias caused by low data utilization will lead to error accumulation along with the self-training process,thus forming irreversible deviation and damaging the performance.In this paper,a curriculum paradigm based on the dynamic weights of samples for semi-supervised learning is proposed,aiming at encouraging the model to utilize samples from easy to hard and gradually construct hyperplanes based on the non-discrete curriculum,so as to alleviate the generation of noise in the pseudo-labeling process and enhance the generalization ability of the mod-el.Specifically,from the intra-class perspective,prototypes of features are constructed by mixing pseudo-labels with high confidence,which can provide weak supervision signals.Then,the learning difficulties of samples are es-timated.From the inter-class perspective,label embedding is used to evaluate the semantic relevancy between cate-gories,and the discrimination between semantically related categories are weaken in the early stage of training.Comprehensive experiments and analyses are conducted on commonly-used semi-supervised learning benchmark datasets to demonstrate the effectiveness of this method.
semi-supervised learningfeature representation vectorcurriculum learningprototype of fea-turessemantic relevancy
国家科技期刊平台
NSTL
万方数据
维普
