Groupwise Label Enhancement Broad Learning System for Image Classification
- 26 March 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cybernetics
- Vol. 55 (7) , 3431-3444
Abstract
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.Keywords
Funding Information
- National Natural Science Foundation of China (62106068, 62106233)
- Science and Technology Innovation Talent Project of Henan Province University (25HASTIT028, KFJJ2022001, CSKFJJ-2024-4, CSKFJJ-2025-8)
- Cultivation Project of Tuoxin Team in Henan University of Technology
This publication has 38 references indexed in Scilit:
- Reinforced Collaborative-Competitive Representation for Biomedical Image RecognitionInterdisciplinary Sciences: Computational Life Sciences, 2025
- Label enhancement via manifold approximation and projection with graph convolutional networkPattern Recognition, 2024
- Transformer-BLS: An efficient learning algorithm based on multi-head attention mechanism and incremental learning algorithmsExpert Systems with Applications, 2023
- A Novel Label Enhancement Algorithm Based on Manifold LearningPattern Recognition, 2022
- Regularized discriminative broad learning system for image classificationKnowledge-Based Systems, 2022
- Communicating sentiment and outlook reverses inaction against collective risksProceedings of the National Academy of Sciences, 2020
- Discriminative graph regularized broad learning system for image recognitionScience China Information Sciences, 2018
- Exploiting a cognitive bias promotes cooperation in social dilemma experimentsNature Communications, 2018
- Inter-class sparsity based discriminative least square regressionNeural Networks, 2018
- Extreme learning machine: Theory and applicationsNeurocomputing, 2006