Litcius/Paper detail

Dynamic Double Classifiers Approximation for Cross-Domain Recognition

Xiaozhao Fang, Na Han, Guoxu Zhou, Shohua Teng, Yong Xu, Shenli Xie

2020IEEE Transactions on Cybernetics30 citationsDOI

Abstract

In general, existing cross-domain recognition methods mainly focus on changing the feature representation of data or modifying the classifier parameter and their efficiencies are indicated by the better performance. However, most existing methods do not simultaneously integrate them into a unified optimization objective for further improving the learning efficiency. In this article, we propose a novel cross-domain recognition algorithm framework by integrating both of them. Specifically, we reduce the discrepancies in both the conditional distribution and marginal distribution between different domains in order to learn a new feature representation which pulls the data from different domains closer on the whole. However, the data from different domains but the same class cannot interlace together enough and thus it is not reasonable to mix them for training a single classifier. To this end, we further propose to learn double classifiers on the respective domain and require that they dynamically approximate to each other during learning. This guarantees that we finally learn a suitable classifier from the double classifiers by using the strategy of classifier fusion. The experiments show that the proposed method outperforms over the state-of-the-art methods.

Topics & Concepts

Classifier (UML)Computer scienceArtificial intelligencePattern recognition (psychology)Machine learningLabeled dataRandom subspace methodFeature learningDomain Adaptation and Few-Shot LearningMachine Learning and ELMNeonatal and fetal brain pathology