南京大学学报(自然科学版) ›› 2020, Vol. 56 ›› Issue (4): 533–540.doi: 10.13232/j.cnki.jnju.2020.04.011
基于深度特征表示的Softmax聚类算法
陈俊芬(
),赵佳成,韩洁,翟俊海
- 河北省机器学习与计算智能重点实验室，河北大学数学与信息科学学院，保定，071002
Softmax clustering algorithm based on deep features representation
Junfen Chen(),Jiacheng Zhao,Jie Han,Junhai Zhai
- Hebei Key Laboratory of Machine Learning and Computational Intelligence，College of Mathematics andInformation Science，Hebei University，Baoding，071002, China
摘要：
图像和语音已成为日常生活和科研的常见数据类型，图像的聚类分析是数据挖掘和图像处理领域的重要任务之一.基于自编码器的深度聚类方法具有表征能力有限的缺点，并且特征的生成与聚类指派是分步进行的.为此，提出一种基于新颖卷积自编码器的深度Softmax聚类算法(Asymmetric Convolutional Auto?encoder Based Softmax Clustering, ASCAE?Softmax).首先设计一种非对称的卷积自编码器网络结构(ASCAE)，通过优化卷积和添加全连接层，使整个网络呈非对称；接着使用Softmax聚类器把特征映射成聚类概率分布，构造辅助目标概率分布，将特征学习与聚类判别联合在一起.通过迭代最小化KL(Kullback?Leibler)散度损失达到清晰的聚类划分.实验结果表明，该方法能够学习出使同类更加紧凑、异类更加稀疏的特征表示，且聚类结果优于经典的深度聚类算法.
中图分类号:
- TP391
| 1 | Zhang L H，Qi G J，Wang L Q，et al. vs AET. AED：unsupervised representation learning by auto?encoding transformations rather than data∥2009 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach，CA，USA：IEEE，2019：2547-2555. |
| 2 | Kang G L，Jiang L，Yang Y，et al. Contrastive adaptation network for unsupervised domain adaptation∥2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach，CA，USA：IEEE，2019：4893-4902. |
| 3 | Wu Z R，Xiong Y J，Yu S X，et al. Unsupervised feature learning via non?parametric instance discrimination∥2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City，UT，USA：IEEE，2018：3733-3742. |
| 4 | Caron M，Bojanowski P，Joulin A，et al. Deep clustering for unsupervised learning of visual features∥The 15th European Conference on Computer Vision (ECCV). Springer Berlin Heidelberg，2018：132-149. |
| 5 | Dizaji K G，Herandi A，Deng C，et al. Deep clustering via joint convolutional autoencoder embedding and relative entropy minimization∥2017 IEEE International Conference on Computer Vision (ICCV). Venice，Italy：IEEE，2017：5736-5745. |
| 6 | Li F F，Qiao H，Zhang B，et al. Discriminatively boosted image clustering with fully convolutional |
| auto?encoders. Pattern Recognition，2018，83：161-173. | |
| 7 | Yang J W，Parikh D，Batra D. Joint unsupervised learning of deep representations and image clusters∥2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas，NV，USA：IEEE，2016：5147-5156. |
| 8 | Xie J Y，Girshick R，Farhadi A. Unsupervised deep embedding for clustering analysis. 2016，arXiv:1511.06335. |
| 9 | Radford A，Metz L，Chintala S. Unsupervised representation learning with deep convolutional generative adversarial networks. arxiv：1511.06434，2015. |
| 10 | Wang W G，Song H M，Zhao S Y，et al. Learning unsupervised video object segmentation through visual attention∥IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach，CA，USA：IEEE，2019：3064-3074. |
| 11 | He K M，Fan H Q，Wu Y X，et al. Momentum contrast for unsupervised visual representation learning. arXiv:1911.05722，2020. |
| 12 | Vo V H，Bach F，Cho M，et al. Unsupervised image matching and object discovery as optimization∥IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach，CA，USA：IEEE，2019：8287-8296. |
| 13 | Fischer A，Igel C. An introduction to restricted Boltzmann machines∥Alvarez L，Mejail M，Gomez L，et al. Progress in pattern recognition，image analysis，computer vision，and applications (CIARP). Springer Berlin Heidelberg，2012：14-36. |
| 14 | Rumelhart D E，Hinton G E，Williams R J. Learning representations by back?propagating errors. Nature，1986，323(6088)：533-536. |
| 15 | Lecun Y，Bottou L，Bengio Y，et al. Gradient?based learning applied to document recognition. Proceedings of the IEEE，1998，86(11)：2278-2324. |
| 16 | Dosovitskiy A，Springenberg J T，Riedmiller M，et al. Discriminative unsupervised feature learning with convolutional neural networks∥Proceedings of the 27th International Conference on Neural Information Processing Systems. Montreal，Canada：MIT Press，2014：766-774. |
| 17 | Hinton G E，Salakhutdinov R R. Reducing the dimensionality of data with neural networks. Science，2006，313(5786)：504-507. |
| 18 | Masci J，Meier U，Cire?an D，et al. Stacked convolutional auto?encoders for hierarchical feature extraction∥The 21th International Conference on Artificial Neural Networks. Springer Berlin Heidelberg，2011：52-59. |
| 19 | Goodfellow I，Pouget?Abadie J，Mirza M，et al. Generative adversarial nets∥Proceedings of the 27th International Conference on Neural Information Processing Systems. Montreal，Canada：MIT Press，2014：2672-2680. |
| 20 | Caron M，Bojanowski P，Mairal J，et al. Unsupervised pre?training of image features on non?curated data∥2019 IEEE/CVF International Conference on Computer Vision (ICCV). Seoul，Korea (South)：IEEE，2019：2959-2968. |
| 21 | Ji X，Vedaldi A，Henriques J F. Invariant information clustering for unsupervised image classification and segmentation∥2019 IEEE/CVF International Conference on Computer Vision (ICCV). Seoul，Korea (South)：IEEE，2019：9865-9874. |
| 22 | Van Der Maaten L，Hinton G. Visualizing data using t?SNE. Journal of Machine Learning Research，2008，9：2579-2605. |
| 23 | Springenberg J T，Dosovitskiy A，Brox T，et al. Striving for simplicity：the all convolutional net. 2015，arXiv:1412.6806. |
| [1] | 吕国俊,曹建军,郑奇斌,常宸,翁年凤. 基于结构保持对抗网络的跨模态实体分辨[J]. 南京大学学报(自然科学版), 2020, 56(2): 197-205. |
|