自动化学报2025，Vol.51Issue(6)：1388-1402,15.DOI:10.16383/j.aas.c240734
松弛图嵌入的判别宽度学习系统以及在视觉识别中的应用
Relaxed-graph Embedding Discriminative Broad Learning System and Its Application in Visual Recognition
摘要
Abstract
The broad learning system,as a lightweight network,achieves a good balance between efficiency and ac-curacy.However,it primarily relies on strict binary labels for supervision and neglects local structural information during data transformation,limiting the model's performance.To address this issue,this paper proposes a relaxed-graph embedding discriminative broad learning system model and applies it to visual recognition,with the goal of enhancing model performance through the introduction of flexible labels and a relaxed-graph structure.The innova-tions of this paper are as follows:1)We innovatively use double transformation matrices to construct the relaxed-graph,separating the responsibilities of the transformation matrix.This reduces the burden on the transformation matrix and allows for the learning of more flexible transformation matrix,thereby mitigating the overfitting prob-lem;2)We introduce a flexible label strategy that increases the distance between different categories labels,address-ing the issue of strict binary labels,and thereby enhancing the model's discriminative ability;3)An iterative optim-ization algorithm based on the alternating direction method of multipliers is proposed to achieve efficient model op-timization.Extensive experiments on facial image datasets,object image datasets,scene image datasets and hand-written character image datasets demonstrate that the proposed model outperforms other advanced recognition al-gorithms.关键词
宽度学习系统/松弛图/柔性标签/视觉识别Key words
Broad learning system/relaxed-graph/flexible label/visual recognition引用本文复制引用
金军委,常少凯,耿彪,李艳婷,赵孟,王震,陈俊龙,李鹏..松弛图嵌入的判别宽度学习系统以及在视觉识别中的应用[J].自动化学报,2025,51(6):1388-1402,15.基金项目
国家自然科学基金(62106068,62106233,62073123,62375078,U1813203),河南省科技攻关项目(222102210058,232102210062,232102210007)资助Supported by National Natural Science Foundation of China(62106068,62106233,62073123,62375078,U1813203)and Sci-ence and Technology Research Project of Henan Province(222102210058,232102210062,232102210007) （62106068,62106233,62073123,62375078,U1813203）
