Convolutional Attention in Ensemble With Knowledge Transferred for Remote Sensing Image Classification

Ensemble learning is one of the hottest topics in machine learning. In this letter, we develop a convolutional attention in ensemble (CAE) method, which, for the first time, introduces attention-based weighting scheme into ensemble learning. The knowledge contained in base classifiers is transferred into the final classifier, by which the base classifier with a higher performance could be given much more attention. In particular, we employ convolutional attention models to develop an efficient ensemble classifier for image classification. Our CAE can leverage the representation capacity of convolutional neural networks to enhance the performance of ensemble classifiers. We apply our method to remote sensing image classification tasks, which achieves much better performance than the state of the arts.

[1]  Chen Chen,et al.  Output Constraint Transfer for Kernelized Correlation Filter in Tracking , 2016, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[2]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[3]  Lei Guo,et al.  Remote Sensing Image Scene Classification Using Bag of Convolutional Features , 2017, IEEE Geoscience and Remote Sensing Letters.

[4]  Chen Chen,et al.  Memory Attention Networks for Skeleton-Based Action Recognition , 2018, IEEE Transactions on Neural Networks and Learning Systems.

[5]  Tony R. Martinez,et al.  Decision Tree Ensemble: Small Heterogeneous Is Better Than Large Homogeneous , 2008, 2008 Seventh International Conference on Machine Learning and Applications.

[6]  Rafael A. Calvo,et al.  Accuracy and Diversity in Ensembles of Text Categorisers , 2005, CLEI Electron. J..

[7]  Xiaoqiang Lu,et al.  Remote Sensing Image Scene Classification: Benchmark and State of the Art , 2017, Proceedings of the IEEE.

[8]  Anders Krogh,et al.  Learning with ensembles: How overfitting can be useful , 1995, NIPS.

[9]  Ludmila I. Kuncheva,et al.  Measures of Diversity in Classifier Ensembles and Their Relationship with the Ensemble Accuracy , 2003, Machine Learning.

[10]  Xuelong Li,et al.  Scene Classification With Recurrent Attention of VHR Remote Sensing Images , 2019, IEEE Transactions on Geoscience and Remote Sensing.

[11]  Chen Chen,et al.  One-Two-One Networks for Compression Artifacts Reduction in Remote Sensing , 2018, ISPRS Journal of Photogrammetry and Remote Sensing.

[12]  Hainan Wang,et al.  The random boosting ensemble classifier for land-use image classification , 2018, Multimedia Tools and Applications.

[13]  Hongming Zhou,et al.  Extreme Learning Machine for Regression and Multiclass Classification , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[14]  Jie Gui,et al.  A novel method for recognizing face with partial occlusion via sparse representation , 2013 .

[15]  Yoshua Bengio,et al.  How transferable are features in deep neural networks? , 2014, NIPS.

[16]  Qian Du,et al.  GETNET: A General End-to-End 2-D CNN Framework for Hyperspectral Image Change Detection , 2019, IEEE Transactions on Geoscience and Remote Sensing.

[17]  Lu Wang,et al.  Land-use scene classification using multi-scale completed local binary patterns , 2015, Signal, Image and Video Processing.

[18]  Alex Graves,et al.  Recurrent Models of Visual Attention , 2014, NIPS.

[19]  Xin Yao,et al.  Diversity creation methods: a survey and categorisation , 2004, Inf. Fusion.

[20]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[21]  Xuelong Li,et al.  Locality and Structure Regularized Low Rank Representation for Hyperspectral Image Classification , 2019, IEEE Transactions on Geoscience and Remote Sensing.

[22]  Ling Shao,et al.  Action Recognition Using 3D Histograms of Texture and A Multi-Class Boosting Classifier , 2017, IEEE Transactions on Image Processing.

[23]  Tieniu Tan,et al.  Representative Vector Machines: A Unified Framework for Classical Classifiers , 2016, IEEE Transactions on Cybernetics.