| 71 | 0 | 21 |
| 下载次数 | 被引频次 | 阅读次数 |
图像聚类旨在挖掘图像数据潜在的模式与规则，研究针对现有方法依赖内在特征而忽视外在语义特征致聚类效果欠佳的问题，提出新的深度图像聚类方法。该方法借助CLIP (Contrastive Language-Image Pretraining)模型挖掘语义特征，构建跨模态融合策略整合图像与文本信息，结合Kmeans算法构建深度聚类框架。在STL-10、CIFAR-10和CIFAR-20数据集上与15种已有方法及CLIP零样本分类方法对比实验，实验结果表明本文提出的图像聚类方法的聚类性能在多个指标上得到了显著提升。
Abstract：Image clustering aims to mine the potential patterns and rules of image data. Existing methods rely primarily on intrinsic features while neglecting external semantic features, resulting in an issue of suboptimal clustering. For this, a novel deep image clustering method is proposed here. This method excavates semantic features through CLIP model, constructs a cross-modal fusion strategy to integrate image and text information, and builds a deep clustering framework combined with Kmeans algorithm. Compared with 15 existing methods and CLIP zero sample classification method in STL-10, CIFAR-10 and CIFAR-20 data sets, the results show that the proposed method significantly improves clustering performance in clustering accuracy(ACC), normalized mutual information(NMI) and adjusting the Rand index(ARI) index. The proposed method provides a new avenue for image clustering and is expected to advance the development of related fields.
[ 1 ] Jain A K,Murty M N,Flynn P J.Data clustering:A review[J].ACM computing surveys,1999,31(3):264-323.
[ 2 ] 韩家炜，裴健，范明，等.数据挖掘：概念与技术[M].北京：机械工业出版社，2012.
[ 3 ] Walters P G P.Global market segmentation:methodologies and challenges[J].Journal of Marketing Management,1997,13(1-3):165-177.
[ 4 ] 孙杰.聚类算法分析在基因表达数据中的分析应用[D].镇江：江苏科技大学，2012.
[ 5 ] Cai D,He X,Han J,et al.Graph regularized nonnegative matrix factorization for data representation[J].IEEE transactions on pattern analysis and machine intelligence,2010,33(8):1548-1560.
[ 6 ] 刘丽端.基于聚类的图像检索技术研究[D].武汉：武汉理工大学，2012.
[ 7 ] 何俊，葛红，王玉峰.图像分割算法研究综述[J].计算机工程与科学，2009,31(12):58.
[ 8 ] Guo X,Liu X,Zhu E,et al.Deep clustering with convolutional autoencoders[C]//Neural Information Processing:24th International Conference,ICONIP 2017.Guangzhou,China,2017:373-382.
[ 9 ] Chen T,Lu S,Fan J.SS-HCNN:Semi-supervised hierarchical convolutional neural network for image classification[J].IEEE Transactions on Image Processing,2018,28(5):2389-2398.
[10] Wang Y,Wang J,Zhang W.Deep mutual information decoupling based unsupervised image clustering[J].Journal of Applied Science and Engineering,28(6):1321-1329.
[11] 孙明浩，王洪元，吴琳钰，等.基于特征金字塔分支和非局部关注的行人重识别[J].数据采集与处理，2023,38(1):121-131.
[12] Park S,Han S,Kim S,et al.Improving unsupervised image clustering with robust learning[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.Nashville,TN,USA,2021:12278 - 12287.
[13] Li Y,Liang F,Zhao L,et al.Supervision exists everywhere:A data efficient contrastive language-image pre-training paradigm[EB/OL].(2023-03-14)[2024-12-01].http://arxiv.org/abs/2110.05208.
[14] 姬强，孙艳丰，胡永利，等.深度聚类算法研究综述[J].北京工业大学学报，2021,47(8):912-924.
[15] 夏金泽，孙浩铭，胡盛辉，等.基于图像信息约束的三维激光点云聚类方法[J].光电工程，2023,50(2):220148.
[16] Xie J,Girshick R,Farhadi A.Unsupervised deep embedding for clustering analysis[C]//33rd International Conference on Machine Learning,ICML 2016.New York City,NY,USA,2016:478-487.
[17] Miller G A.WordNet:a lexical database for English[J].Communications of the ACM,1995,38(11):39-41.
[18] Ahmed M,Seraj R,Islam S M S.The k-means algorithm:A comprehensive survey and performance evaluation[J].Electronics,2020,9(8):1295.
[19] Yang J,Parikh D,Batra D.Joint unsupervised learning of deep representations and image clusters[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Las Vegas,NV,United States,2016:5147-5156.
[20] Chang J,Wang L,Meng G,et al.Deep adaptive image clustering[C]//Proceedings of the IEEE International Conference on Computer Vision.Venice,Italy,2017:5879-5887.
[21] Wu J,Long K,Wang F,et al.Deep comprehensive correlation mining for image clustering[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision.Seoul,Korea,2019:8150-8159.
[22] Ji X,Henriques J F,Vedaldi A.Invariant information clustering for unsupervised image classification and segmentation[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision.Seoul,Korea,2019:9865-9874.
[23] Huang J,Gong S,Zhu X.Deep semantic clustering by partition confidence maximisation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.Seattle,WA,USA,2020:8849-8858.
[24] Li Y,Hu P,Liu Z,et al.Contrastive clustering[C]//Proceedings of the AAAI Conference on Artificial Intelligence.Vancouver,Canada,2021,35(10):8547-8555.
[25] Tao Y,Takagi K,Nakata K.Clustering-friendly representation learning via instance discrimination and feature decorrelation[EB/OL].(2021-05-31)[2024-12-01].http://arxiv.org/ais/2106.00131.
[26] Van Gansbeke W,Vandenhende S,Georgoulis S,et al.Scan:Learning to classify images without labels[C]//European Conference on Computer Vision.Glasgow,UK,2020:268-285.
[27] Tsai T W ,Li C ,Zhu J .MiCE:Mixture of contrastive experts for unsupervised image clustering[EB/OL].(2021-05-03)[2024-12-01].http://arxiv.org/abs/2105.01899.
[28] Zhong H,Wu J,Chen C,et al.Graph contrastive clustering[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision.Montreal,Canada,2021:9224-9233.
[29] Dang Z,Deng C,Yang X,et al.Nearest neighbor matching for deep clustering[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.Nashville,Tennessee,USA,2021:13693-13702.
[30] Niu C,Shan H,Wang G.Spice:Semantic pseudo-labeling for image clustering[J].IEEE Transactions on Image Processing,2022,31:7264-7278.
[31] Tan D,Huang Z,Peng X,et al.Deep adaptive fuzzy clustering for evolutionary unsupervised representation learning[J].IEEE Transactions on Neural Networks and Learning Systems,2024,35(5),6103-6117.
[32] Liang C,Dong Z,Yang S,et al.Jointly Learn the Base Clustering and Ensemble for Deep Image Clustering[C]//2024 IEEE International Conference on Multimedia and Expo (ICME).Niagara Falls,Canada,2024:1-6.
基本信息:
DOI：
中图分类号:TP391.41;TP311.13
引用信息:
[1]韩胜强,曲建华.基于语义增强的深度图像聚类方法研究[J].山东师范大学学报(自然科学版),2024,39(04):358-366.
基金信息:
国家自然科学基金资助项目(61876101,62102236)