Collaborative representation with curriculum classifier boosting for unsupervised domain adaptation
作者：
Highlights：
• We present a novel unsupervised domain adaptation solution based on collaborative representation which seeks for the close samples between domains and uses them to assist further predictions. Plenty of experiments validate the effectiveness of our method and more general, we can solve domain adaptation problems without reducing domain discrepancy explicitly, which is different from previous methods.
• Curriculum sample choosing is proposed to select the close samples between domains based on reconstruction residual. Then these samples are added to training set for subsequent prediction.
• We propose distance-aware sparsity regularization to learn more reasonable representation, so that samples have smaller distance to the query sample are intended to have larger weights.
摘要
•We present a novel unsupervised domain adaptation solution based on collaborative representation which seeks for the close samples between domains and uses them to assist further predictions. Plenty of experiments validate the effectiveness of our method and more general, we can solve domain adaptation problems without reducing domain discrepancy explicitly, which is different from previous methods.•Curriculum sample choosing is proposed to select the close samples between domains based on reconstruction residual. Then these samples are added to training set for subsequent prediction.•We propose distance-aware sparsity regularization to learn more reasonable representation, so that samples have smaller distance to the query sample are intended to have larger weights.
论文关键词：Domain adaptation,Collaborative representation,Curriculum learning,Classifier boosting
论文评审过程：Received 1 June 2020, Revised 17 September 2020, Accepted 26 December 2020, Available online 8 January 2021, Version of Record 19 January 2021.
论文官网地址：https://doi.org/10.1016/j.patcog.2020.107802
