Cross-Scatter Sparse Dictionary Pair Learning for Cross-Domain Classification

作     者：Jiang, Lin Wu, Jigang Zhao, Shuping Li, Jiaxing 

作者机构：Guangdong Univ Technol Sch Comp Sci & Technol Guangzhou 510006 Peoples R China Dongguan South China Design Innovat Inst Dongguan 523781 Peoples R China Guangzhou Univ Sch Artificial Intelligence Guangzhou 510006 Peoples R China 

出 版 物：《IEEE TRANSACTIONS ON MULTIMEDIA》 (IEEE Trans Multimedia)

年 卷 期：2025年第27卷

页      面：371-384页

核心收录：

学科分类：0810[工学-信息与通信工程] 0808[工学-电气工程] 08[工学] 0835[工学-软件工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：Natural Science Foundation of China [62072118, 62106052, 62302112] Guangdong Natural Science Foundation [2023A1515011230] Guangdong Basic and Applied Basic Research Foundation [2021B1515120010, 2024A1515011647] Key-Area R&D Program of Dongguan Guangdong Pearl River Talent Program [2023QN10X503] Guangzhou Basic and Applied Basic Research Foundation [2025A04J3378] 

主　　题：Dictionary learning scatter learning sparse coding cross-domain classification Dictionary learning scatter learning sparse coding cross-domain classification 

摘      要：In cross-domain recognition tasks, the divergent distributions of data acquired from various domains degrade the effectiveness of knowledge transfer. Additionally, in practice, cross-domain data also contain a massive amount of redundant information, usually disturbing the training processes of cross-domain classifiers. Seeking to address these issues and obtain efficient domain-invariant knowledge, this paper proposes a novel cross-domain classification method, named cross-scatter sparse dictionary pair learning (CSSDL). Firstly, a pair of dictionaries is learned in a common subspace, in which the marginal distribution divergence between the cross-domain data is mitigated, and domain-invariant information can be efficiently extracted. Then, a cross-scatter discriminant term is proposed to decrease the distance between cross-domain data belonging to the same class. As such, this term guarantees that the data derived from same class can be aligned and that the conditional distribution divergence is mitigated. In addition, a flexible label regression method is introduced to match the feature representation and label information in the label space. Thereafter, a discriminative and transferable feature representation can be obtained. Moreover, two sparse constraints are introduced to maintain the sparse characteristics of the feature representation. Extensive experimental results obtained on public datasets demonstrate the effectiveness of the proposed CSSDL approach.