DEEP ENSEMBLE LEARNING MODEL BASED ON COVARIANCE POOLING OF MULTI-LAYER CNN FEATURES

被引:0
|
作者
Akodad, Sara [1 ,2 ]
Bombrun, Lionel [1 ]
Puscasu, Maria [1 ]
Xia, Junshi [3 ]
Germain, Christian [1 ]
Berthoumieu, Yannick [1 ]
机构
[1] Univ Bordeaux, CNRS, IMS, UMR 5218,Grp Signal & Image, F-33405 Talence, France
[2] Ctr Natl Etud Spatiales, CNES, 18 Ave Edouard Belin, F-31400 Toulouse, France
[3] RIKEN, RIKEN Ctr Adv Intelligence Project AIP, Tokyo 1030027, Japan
关键词
Covariance pooling; multi-layer representation; ensemble learning; CNN;
D O I
10.1109/ICIP46576.2022.9897868
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Compared to standard deep convolutional neural networks (CNN) which include a global average pooling operator, second-order neural networks have a global covariance pooling operator which allows to capture richer statistics of CNN features. They have been shown to improve representation and generalization abilities. However, this covariance pooling is performed only on the deepest CNN feature maps. To benefit from different levels of abstraction, we propose to extend these models by using a multi-layer approach. In addition, to obtain better predictive performance, an end-to-end ensemble learning architecture is proposed. Experiments are conducted on four datasets and have confirmed the potential of the proposed model for various image processing applications such as remote sensing scene classification, indoor scene recognition and texture classification.
引用
收藏
页码:1081 / 1085
页数:5
相关论文
共 50 条
  • [41] Image Classification Algorithm Based on Deep Neural Network and Multi-Layer Feature Learning
    Guo, Guangxing
    [J]. BASIC & CLINICAL PHARMACOLOGY & TOXICOLOGY, 2019, 124 : 287 - 287
  • [42] Learning-Based THz Multi-Layer Imaging With Model-Based Masks
    Wang, P.
    Koike-Akino, T.
    Boufounos, P.
    Tsujita, W.
    Yamashita, G.
    Fukuta, T.
    Nakajima, M.
    [J]. 2023 48TH INTERNATIONAL CONFERENCE ON INFRARED, MILLIMETER, AND TERAHERTZ WAVES, IRMMW-THZ, 2023,
  • [43] Universal Online Learning with Gradient Variations: A Multi-layer Online Ensemble Approach
    Yan, Yu-Hu
    Zhao, Peng
    Zhou, Zhi-Hua
    [J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 36 (NEURIPS 2023), 2023,
  • [44] A deep learning model for depression detection based on MFCC and CNN generated spectrogram features
    Das, Arnab Kumar
    Naskar, Ruchira
    [J]. BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2024, 90
  • [45] CLASSIFICATION OF GPR SIGNALS VIA COVARIANCE POOLING ON CNN FEATURES WITHIN A RIEMANNIAN FRAMEWORK
    Gallet, Matthieu
    Mian, Ammar
    Ginolhac, Guillaume
    Stelzenmuller, Nickolas
    [J]. 2022 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2022), 2022, : 365 - 368
  • [46] An Intelligent Network Traffic Prediction Scheme Based on Ensemble Learning of Multi-Layer Perceptron in Complex Networks
    Wang, Chunzhi
    Cao, Weidong
    Wen, Xiaodong
    Yan, Lingyu
    Zhou, Fang
    Xiong, Neal
    [J]. ELECTRONICS, 2023, 12 (06)
  • [47] A Multi-Layer Dual Attention Deep Learning Model With Refined Word Embeddings for Aspect-Based Sentiment Analysis
    Rida-E-Fatima, Syeda
    Javed, Ali
    Banjar, Ameen
    Irtaza, Aun
    Dawood, Hassan
    Dawood, Hussain
    Alamri, Abdullah
    [J]. IEEE ACCESS, 2019, 7 : 114795 - 114807
  • [48] Developing a Multi-Layer Deep Learning Based Predictive Model to Identify DNA N4-Methylcytosine Modifications
    Zeng, Rao
    Liao, Minghong
    [J]. FRONTIERS IN BIOENGINEERING AND BIOTECHNOLOGY, 2020, 8
  • [49] Fast fourier transform based new pooling layer for deep learning
    Hamad, Aqeel Mohsin
    [J]. INTERNATIONAL JOURNAL ON SMART SENSING AND INTELLIGENT SYSTEMS, 2022, 15 (01):
  • [50] Scientific text citation analysis using CNN features and ensemble learning model
    Alnowaiser, Khaled
    [J]. PLOS ONE, 2024, 19 (05):