ABSTRACT
During the rapid development of deep learning, the multi-label recognition task has achieved pretty performance. Recently, the emergence of graph convolution network (GCN) has further improved the accuracy of multi-label recognition. However, in the learning process, how to better represent the feature information of labels and innovatively design structures to obtain good recognition performance is still unclear. To solve these problems, we propose a partitioning graph convolutional network framework for multi-label recognition. First, we segregate the computational graph into multiple sub-graphs. Then, we perform batch normalization operation on each output layer, which can further improve the recognition performance of the network. Finally, extensive experiments are carried out on a multi-label PPT dataset, showing that our proposed solution can greatly improve the feature information utilization of labels and improve the recognition performance.
- W. Liu, H. Wang, X. Shen, and I. Tsang, “The Emerging Trends of Multi-Label Learning,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 14, no. 8, pp. 1–20, 2021.Google Scholar
- T. Chen, L. Lin, R. Chen, X. Hui, and H. Wu, “Knowledge-Guided Multi-Label Few-Shot Learning for General Image Recognition,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 44, no. 3, pp. 1371–1384, 2022.Google ScholarCross Ref
- B. Wei, K. Hao, L. Gao, and X. S. Tang, “Bioinspired Visual-Integrated Model for Multilabel Classification of Textile Defect Images,” IEEE Trans. Cogn. Dev. Syst., vol. 13, no. 3, pp. 503–513, 2021.Google ScholarCross Ref
- H. Peng , “Hierarchical Taxonomy-Aware and Attentional Graph Capsule RCNNs for Large-Scale Multi-Label Text Classification,” IEEE Trans. Knowl. Data Eng., vol. 33, no. 6, pp. 2505–2519, 2021.Google ScholarCross Ref
- M. L. Zhang and Z. H. Zhou, “ML-KNN: A lazy learning approach to multi-label learning,” Pattern Recognit., vol. 40, no. 7, pp. 2038–2048, 2007.Google ScholarDigital Library
- Y. Liu, K. Wen, Q. Gao, X. Gao, and F. Nie, “SVM based multi-label learning with missing labels for image annotation,” Pattern Recognit., vol. 78, pp. 307–317, 2018.Google ScholarDigital Library
- R. Wang, S. Ye, K. Li, and S. Kwong, “Bayesian network based label correlation analysis for multi-label classifier chain,” Inf. Sci. (Ny)., vol. 554, pp. 256–275, 2021.Google ScholarCross Ref
- C. Li, C. Liu, L. Duan, P. Gao, and K. Zheng, “Reconstruction Regularized Deep Metric Learning for Multi-Label Image Classification,” IEEE Trans. Neural Networks Learn. Syst., vol. 31, no. 7, pp. 2294–2303, 2020.Google Scholar
- T. Nguyen and R. Raich, “Incomplete Label Multiple Instance Multiple Label Learning,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 44, no. 3, pp. 1320–1337, 2022.Google ScholarCross Ref
- D. Wang and S. Zhang, “Unsupervised person re-identification via multi-label classification,” Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., pp. 10978–10987, 2020.Google ScholarCross Ref
- Q. Li, X. Peng, Y. Qiao, and Q. Hao, “Unsupervised person re-identification with multi-label learning guided self-paced clustering,” Pattern Recognit., vol. 125, p. 108521, 2022.Google ScholarDigital Library
- S. Gidaris, N. Komodakis, and P. Paristech, “Generating Classification Weights with GNN Denoising Autoencoders for Few-Shot Learning,” Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp. 21–30, 2019.Google ScholarCross Ref
- T. N. Kipf and M. Welling, “Semi-supervised classification with graph convolutional networks,” 5th Int. Conf. Learn. Represent. ICLR 2017, pp. 1–14, 2017.Google Scholar
- W. L. Chiang, Y. Li, X. Liu, S. Bengio, S. Si, and C. J. Hsieh, “Cluster-GCN: An efficient algorithm for training deep and large graph convolutional networks,” Proc. ACM SIGKDD Int. Conf. Knowl. Discov. Data Min., pp. 257–266, 2019.Google ScholarDigital Library
- S. Joseph, “Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift,” Journal. Pract., vol. 10, no. 6, pp. 730–743, 2016.Google ScholarCross Ref
- B. Lehne and T. Schlitt, “Protein-protein interaction databases: keeping up with growing interactomes.,” Hum. Genomics, vol. 3, no. 3, pp. 291–297, 2009.Google ScholarCross Ref
- Q. Shi and H. Zhang, “Fault Diagnosis of an Autonomous Vehicle with an Improved SVM Algorithm Subject to Unbalanced Datasets,” IEEE Trans. Ind. Electron., vol. 68, no. 7, pp. 6248–6256, 2021.Google ScholarCross Ref
- B. Wei, K. Hao, L. Gao, X. Tang, and Y. Zhao, “A biologically inspired visual integrated model for image classification,” Neurocomputing, vol. 405, pp. 103–113, 2020.Google ScholarCross Ref
- A. Krizhevsky and G. E. Hinton, “ImageNet Classification with Deep Convolutional Neural Networks,” in Proc. IEEE Conf. neural information processing systems, pp. 1–9.Google Scholar
- J. Chen, L. Jiao, X. Liu, L. Li, F. Liu, and S. Yang, “Automatic Graph Learning Convolutional Networks for Hyperspectral Image Classification,” IEEE Trans. Geosci. Remote Sens., vol. 60, pp. 1–13, 2022.Google Scholar
Index Terms
- Part-GCNet: Partitioning Graph Convolutional Network for Multi-Label Recognition
Recommendations
Instance Annotation for Multi-Instance Multi-Label Learning
Special Issue on ACM SIGKDD 2012Multi-instance multi-label learning (MIML) is a framework for supervised classification where the objects to be classified are bags of instances associated with multiple labels. For example, an image can be represented as a bag of segments and ...
Dynamic Label Propagation for Semi-supervised Multi-class Multi-label Classification
ICCV '13: Proceedings of the 2013 IEEE International Conference on Computer VisionIn graph-based semi-supervised learning approaches, the classification rate is highly dependent on the size of the availabel labeled data, as well as the accuracy of the similarity measures. Here, we propose a semi-supervised multi-class/multi-label ...
Graph Convolutional Network Exploring Label Relations for Multi-label Text Classification
PRICAI 2021: Trends in Artificial IntelligenceAbstractMulti-label Text Classification (MLTC) aims to learn a classifier that is able to automatically annotate a data point with the most relevant subset of labels from an large number of labels. Label semantics and relationships are important ...
Comments