计算机科学 ›› 2019, Vol. 46 ›› Issue (12): 279-285.doi: 10.11896/jsjkx.190200315
张天柱, 邹承明
ZHANG Tian-zhu, ZOU Cheng-ming
摘要: 胶囊网络中动态路由的本质就是聚类算法思想的实现。考虑到已有胶囊网络中的聚类方式需要数据满足一定的分布才能达到最好的效果,且图像特征比较复杂,于是将一种普适性更好的模糊聚类算法作为胶囊网络中的特征整合方式,并添加了一个使用信息熵来度量不确定性的激活值,以区分同一级别胶囊层特征的显著性。同时,借鉴特征金字塔网络的思想,将不同胶囊层的特征采样成相同尺度,然后进行融合独立训练。基于Keras框架进行实验,其结果表明,相比原来的胶囊网络,这种具有新型结构的胶囊网络在MNIST和CIFAR-10上有更高的识别准确率。对比实验证明了模糊聚类算法在胶囊网络上的应用潜力,其改善了原胶囊网络中聚类算法存在局限的问题;也证明了对胶囊网络中不同层的特征进行融合,能够获得包含信息更丰富且表达能力更强的特征。
中图分类号:
[1]LU D,WENG Q.A Survey of Image Classification Methods and Techniques for Improving Classification Performance[J].International Journal of Remote Sensing,2007,28(5):823-870.[2]YANN L,BOTTOU L,BENGIO Y,et al.Gradient-based Learning Applied to Document Recognition[J].Proceedings of the IEEE,1998,86(11):2278-2324.[3]KRIZHEVSKY A,SUTSKEVER I,HINTON G E.ImageNet Classification with Deep Convolutional Neural Networks[C]//NIPS.New York,NY:Curran Associates,2012:1097-1105.[4]ZEILER M D,FERGUS R.Visualizing and Understanding Convolutional Networks[C]//Europen Conference on Computer Vision.Switzerland:Springer,2014:818-833.[5]SIMONYAN K,ZISSERMAN A.Very Deep Convolutional Networks for Large-scale Image Recognition[C]//Computer Vision and Pattern Recognition.Princeton:CVPR Press,2015.[6]SZEGEDY C,LIU W,JIA Y Q,et al.Going Deeper with Convolutions[C]//CVPR.Piscataway,NJ:IEEE,2015:1-9.[7]HE K,ZHANG X Y,REN S Q,et al.Deep Residual Learning for Image Recognition[C]//CVPR.Piscataway,NJ:IEEE,2016:770-778.[8]HUANG G,LIU Z,MAATEN L,et al.Densely Connected Convolutional Networks[C]//Computer Vision and Pattern Recognition.Piscataway,NJ:IEEE,2017:2261-2269.[9]GU Z B,CAO F L.Image Classification algorithm of Multi-layer Forward Artificial Neural Network [J].Computer Science,2018,45(S2):238-243.(in Chinese) 顾哲彬,曹飞龙.多层前向人工神经网络图像分类算法[J].计算机科学,2018,45(S2):238-243.[10]HINTON G E,SRIVASTAVA N,KRIZHEVSKY A,et al.Improving Neural Networks by Pre-venting Co-adaptation of Feature Detectors[C/OL].http://arxiv.org/abs/1207.0580.[11]IOFFE S.SZEGEDY C.Batch Normalization:Accelerating Deep Network Training by Reducing Internal Covariate Shift[C]//International Conference on International Conference on Machine Learning.New York,NY:ACM,2015:448-456.[12]TONG W G,LI M X,ZHANG Y K.Research on Optimization Algorithm of Deep Learning[J].Computer Science,2018,45(S2):155-159.(in Chinese) 仝卫国,李敏霞,张一可.深度学习优化算法研究[J].计算机科学,2018,45(S2):155-159.[13]FU B W,SUN T,LIANG J,et al.Review of Principle and Application of Deep Learning[J].Computer Science,2018,45(S1):11-15.(in Chinese) 付文博,孙涛,梁藉,等.深度学习原理及应用综述[J].计算机科学,2018,45(S1):11-15.[14]SABOUR S,FROSST N,HINTON G E.Dynamic Routing between Capsules[C]//NIPS.New York,NY:Curran Associates,2017:3859-3869.[15]HINTON G E,SABOUR S,FROSST N.Matrix Capsules with EM Routing[C]//International Conference on Learning Representations.Princeton:ICLR Press,2018.[16]JAISWAL A,ABDALMAGEED W,WU Y,et al.CapsuleGAN:Generative Adversarial Capsule Network[C]//EuropenConfe-rence on Computer Vision.Berlin:Springer,2018:526-535.[17]DENG F,PU S L,CHEN X H,et al.Hyperspectral Image Classification with Capsule Network Using Limited Training Samples[J].Sensors,2018,18(9):3153.[18]ZHANG X N,LUO P C,HU X W,et al.Research on Classification Performance of Small-Scale Dataset Based on Capsule Network[C]//International Conference on Robotics and Artificial Intelligence.New York,NY:ACM,2018:24-28.[19]XIANG C Q,ZHANG L,TANG Y,et al.MS-CapsNet:A Novel Multi-Scale Capsule Network[J].IEEE Signal Processing Letters,2018,25(12):1850-1854.[20]BEZDEK J C,EHRLICH R,FULL W.FCM:The Fuzzy c-means Clustering Algorithm[J].Computers & Geosciences,1984,10(2/3):191-203.[21]ADELSON E H,ANDERSON C H,BERGEN J R,et al.Pyramid Methods in Image Processing[J].RCA engineer,1984,29(6),33-41.[22]BELL S,ZITNICK C L,BALA K,et al.Inside-Outside Net:Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks[C]//International Conference on Learning Representations.Piscataway,NJ:IEEE,2016:2874-2883.[23]KONG T,YAO A B,CHEN Y R,et al.HyperNet:Towards Accurate Region Proposal Generation and Joint Object Detection[C]//International Conference on Learning Representations.Piscataway,NJ:IEEE,2016:845-853.[24]LIN T Y,DOLLAR P,GRISHICK R,et al.Feature Pyramid Networks for Object Detection[C]//International Conference on Learning Representations.Piscataway,NJ:IEEE,2017:936-944.[25]FRANCIS D,HUET B,MERIALDO B.Embedding Images and Sentences in a Common Space with a Recurrent Capsule Network[C]//International Workshop on Content-based Multimedia Indexing.Piscataway,NJ:IEEE,2018:1-6. |
[1] | 武红鑫, 韩萌, 陈志强, 张喜龙, 李慕航. 监督和半监督学习下的多标签分类综述 Survey of Multi-label Classification Based on Supervised and Semi-supervised Learning 计算机科学, 2022, 49(8): 12-25. https://doi.org/10.11896/jsjkx.210700111 |
[2] | 杨健楠, 张帆. 一种结合双注意力机制和层次网络结构的细碎农作物分类方法 Classification Method for Small Crops Combining Dual Attention Mechanisms and Hierarchical Network Structure 计算机科学, 2022, 49(6A): 353-357. https://doi.org/10.11896/jsjkx.210200169 |
[3] | 杜丽君, 唐玺璐, 周娇, 陈玉兰, 程建. 基于注意力机制和多任务学习的阿尔茨海默症分类 Alzheimer's Disease Classification Method Based on Attention Mechanism and Multi-task Learning 计算机科学, 2022, 49(6A): 60-65. https://doi.org/10.11896/jsjkx.201200072 |
[4] | 朱旭东, 熊贇. 基于样本分布损失的图像多标签分类研究 Study on Multi-label Image Classification Based on Sample Distribution Loss 计算机科学, 2022, 49(6): 210-216. https://doi.org/10.11896/jsjkx.210300267 |
[5] | 武霖, 孙静宇. 多分支RA胶囊网络及在图像分类中的应用 Multi-branch RA Capsule Network and Its Application in Image Classification 计算机科学, 2022, 49(6): 224-230. https://doi.org/10.11896/jsjkx.210400087 |
[6] | 彭云聪, 秦小林, 张力戈, 顾勇翔. 面向图像分类的小样本学习算法综述 Survey on Few-shot Learning Algorithms for Image Classification 计算机科学, 2022, 49(5): 1-9. https://doi.org/10.11896/jsjkx.210500128 |
[7] | 范新南, 赵忠鑫, 严炜, 严锡君, 史朋飞. 结合注意力机制的多尺度特征融合图像去雾算法 Multi-scale Feature Fusion Image Dehazing Algorithm Combined with Attention Mechanism 计算机科学, 2022, 49(5): 50-57. https://doi.org/10.11896/jsjkx.210400093 |
[8] | 张文轩, 吴秦. 基于多分支注意力增强的细粒度图像分类 Fine-grained Image Classification Based on Multi-branch Attention-augmentation 计算机科学, 2022, 49(5): 105-112. https://doi.org/10.11896/jsjkx.210100108 |
[9] | 许华杰, 陈育, 杨洋, 秦远卓. 基于混合样本自动数据增强技术的半监督学习方法 Semi-supervised Learning Method Based on Automated Mixed Sample Data Augmentation Techniques 计算机科学, 2022, 49(3): 288-293. https://doi.org/10.11896/jsjkx.210100156 |
[10] | 董琳, 黄丽清, 叶锋, 黄添强, 翁彬, 徐超. 人脸伪造检测泛化性方法综述 Survey on Generalization Methods of Face Forgery Detection 计算机科学, 2022, 49(2): 12-30. https://doi.org/10.11896/jsjkx.210900146 |
[11] | 邵海琳, 季怡, 刘纯平, 徐云龙. 基于增强特征金字塔网络的场景文本检测算法 Scene Text Detection Algorithm Based on Enhanced Feature Pyramid Network 计算机科学, 2022, 49(2): 248-255. https://doi.org/10.11896/jsjkx.201100072 |
[12] | 范红杰, 李雪冬, 叶松涛. 面向电子病历语义解析的疾病辅助诊断方法 Aided Disease Diagnosis Method for EMR Semantic Analysis 计算机科学, 2022, 49(1): 153-158. https://doi.org/10.11896/jsjkx.201100125 |
[13] | 陈天荣, 凌捷. 基于特征映射的差分隐私保护机器学习方法 Differential Privacy Protection Machine Learning Method Based on Features Mapping 计算机科学, 2021, 48(7): 33-39. https://doi.org/10.11896/jsjkx.201200224 |
[14] | 陈志文, 王坤, 周广蕴, 王旭, 张晓丹, 朱虎明. 基于胶囊网络及其权重剪枝的SAR图像变化检测方法 SAR Image Change Detection Method Based on Capsule Network with Weight Pruning 计算机科学, 2021, 48(7): 190-198. https://doi.org/10.11896/jsjkx.200800225 |
[15] | 胡京徽, 许鹏. 一种基于图像分类的航空紧固件产品自动分类方法 Automatic Classification of Aviation Fastener Products Based on Image Classification 计算机科学, 2021, 48(6A): 63-66. https://doi.org/10.11896/jsjkx.200900163 |
|