Multiscale Dynamic Curvelet Scattering Network
- 25 November 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 35 (6) , 7999-8012
Abstract
The feature representation learning process greatly determines the performance of networks in classification tasks. By combining multiscale geometric tools and networks, better representation and learning can be achieved. However, relatively fixed geometric features and multiscale structures are always used. In this article, we propose a more flexible framework called the multiscale dynamic curvelet scattering network (MSDCCN). This data-driven dynamic network is based on multiscale geometric prior knowledge. First, multiresolution scattering and multiscale curvelet features are efficiently aggregated in different levels. Then, these features can be reused in networks flexibly and dynamically, depending on the multiscale intervention flag. The initial value of this flag is based on the complexity assessment, and it is updated according to feature sparsity statistics on the pretrained model. With the multiscale dynamic reuse structure, the feature representation learning process can be improved in the following training process. Also, multistage fine-tuning can be performed to further improve the classification accuracy. Furthermore, a novel multiscale dynamic curvelet scattering module, which is more flexible, is developed to be further embedded into other networks. Extensive experimental results show that better classification accuracies can be achieved by MSDCCN. In addition, necessary evaluation experiments have been performed, including convergence analysis, insight analysis, and adaptability analysis.Keywords
Funding Information
- Key Scientific Technological Innovation Research Project by Ministry of Education;
- National Natural Science Foundation of China Innovation Research Group Fund (61621005)
- State Key Program and the Foundation for Innovative Research Groups of the National Natural Science Foundation of China (61836009)
- Major Research Plan of the National Natural Science Foundation of China (91438201, 91438103, 91838303)
- National Natural Science Foundation of China (U1701267, 62076192, 62006177, 61902298, 61573267, 61906150, 62276199)
- Higher Education Discipline Innovation Project
- Program for Cheung Kong Scholars and Innovative Research Team in University (IRT 15R53)
- ST Innovation Project from the Chinese Ministry of Education
- Key Research and Development Program in Shaanxi Province of China (2019ZDLGY03-06)
- National Science Basic Research Plan in Shaanxi Province of China (2019JQ-659, 2022JQ-607)
- China Postdoctoral Fund (2022T150506)
- Scientific Research Project of Education Department in Shaanxi Province of China (20JY023)
- Fundamental Research Funds for the Central Universities (XJS201901, XJS201903, JBF201905, JB211908)
- CAAI-Huawei MindSpore Open Fund, this work will be used on MindSpore Framework
This publication has 55 references indexed in Scilit:
- SAR Image segmentation based on convolutional-wavelet neural network and markov random fieldPattern Recognition, 2017
- Invariant Scattering Convolution NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- Representation Learning: A Review and New PerspectivesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- Group Invariant ScatteringCommunications on Pure and Applied Mathematics, 2012
- Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech RecognitionIEEE Transactions on Audio, Speech, and Language Processing, 2011
- Space-Frequency Quantization for Image Compression With DirectionletsIEEE Transactions on Image Processing, 2007
- Fast Discrete Curvelet TransformsMultiscale Modeling & Simulation, 2006
- The contourlet transform: an efficient directional multiresolution image representationIEEE Transactions on Image Processing, 2005
- Bandelet Image Approximation and CompressionMultiscale Modeling & Simulation, 2005
- The finite ridgelet transform for image representationIEEE Transactions on Image Processing, 2003