TY - JOUR
T1 - Groupwise Label Enhancement Broad Learning System for Image Classification
AU - Jin, Junwei
AU - Chang, Shaokai
AU - Duan, Junwei
AU - Li, Yanting
AU - Ding, Weiping
AU - Wang, Zhen
AU - Chen, C. L.Philip
AU - Li, Peng
N1 - Publisher Copyright:
© 2013 IEEE.
PY - 2025
Y1 - 2025
N2 - The broad learning system (BLS) is a lightweight neural network known for its efficient learning capabilities; however, it is limited by its reliance on a binary label strategy. Existing label enhancement models primarily focus on increasing the distances between labels from different classes, which inadvertently expands the distance within the same category. For classification tasks, maintaining similarity within the intraclass is essential for ensuring the model’s effectiveness. To address this issue, we propose a groupwise label enhancement BLS model that ensures both intraclass similarity and interclass disparity of labels. Specifically, we develop a novel regression target that generalizes existing label enhancement targets in BLS, increasing the distances between labels of different classes while overcoming the constraints imposed by binary labels. Moreover, we design a groupwise constraint to jointly enhance the intraclass similarity and interclass disparity of labels. Additionally, we propose a novel alternating direction method of multipliers-based optimization algorithm to solve our proposed model, ensuring both computational efficiency and theoretical convergence. Experimental results on several public datasets demonstrate the outstanding effectiveness and efficiency of our proposed model compared to other state-of-the-art methods.
AB - The broad learning system (BLS) is a lightweight neural network known for its efficient learning capabilities; however, it is limited by its reliance on a binary label strategy. Existing label enhancement models primarily focus on increasing the distances between labels from different classes, which inadvertently expands the distance within the same category. For classification tasks, maintaining similarity within the intraclass is essential for ensuring the model’s effectiveness. To address this issue, we propose a groupwise label enhancement BLS model that ensures both intraclass similarity and interclass disparity of labels. Specifically, we develop a novel regression target that generalizes existing label enhancement targets in BLS, increasing the distances between labels of different classes while overcoming the constraints imposed by binary labels. Moreover, we design a groupwise constraint to jointly enhance the intraclass similarity and interclass disparity of labels. Additionally, we propose a novel alternating direction method of multipliers-based optimization algorithm to solve our proposed model, ensuring both computational efficiency and theoretical convergence. Experimental results on several public datasets demonstrate the outstanding effectiveness and efficiency of our proposed model compared to other state-of-the-art methods.
KW - Broad learning system (BLS)
KW - groupwise constraint
KW - image classification
KW - label enhancement
UR - http://www.scopus.com/inward/record.url?scp=105001110415&partnerID=8YFLogxK
U2 - 10.1109/TCYB.2025.3550175
DO - 10.1109/TCYB.2025.3550175
M3 - 文章
AN - SCOPUS:105001110415
SN - 2168-2267
JO - IEEE Transactions on Cybernetics
JF - IEEE Transactions on Cybernetics
ER -