Image Classification Model with Feature Flip

被引：0
|
作者：
Kim J.-W. [1 ,2 ]
Ha J.-E. [3 ]
机构：
[1] Graduate School of Automotive Engineering, Seoul National University of Science and Technology
[2] Technology Research Lab
[3] Department of Mechanical and Automotive Engineering, Seoul National University of Science and Technology
来源：
Journal of Institute of Control, Robotics and Systems | 2022年 / 28卷 / 10期
关键词：
Backbone; Classification; Deep learning; Feature map; Flip;
D O I：
10.5302/J.ICROS.2022.22.0108
中图分类号：
学科分类号：
摘要：
After Transformer and ViT, the use of attention in vision is increasing, and the performance has also surpassed the existing convolution layer. Attention uses a linear layer by default. Therefore, attention can be seen as an improvement of the linear layer. The direction of improvement of linear and convolution layers is similar when looking at the contents studied so far. The biggest difference between the two is the size of the receptive field. In this paper, various types of FlipConv blocks are presented. In particular, FlipConv block type4 shows similar performance to ConvNeXt block with a small parameter increase. And it shows that the performance of about 8% is good for the data in the form not used for learning. © ICROS 2022.
引用
收藏
页码：903 / 909
页数：6
相关论文
共 50 条
  • [21] A Hybrid Image Feature Descriptor for Classification
    Dawood, Hassan
    Dawood, Hussian
    Guo, Ping
    2015 11TH INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND SECURITY (CIS), 2015, : 58 - 61
  • [22] Feature Mining for Hyperspectral Image Classification
    Jia, Xiuping
    Kuo, Bor-Chen
    Crawford, Melba M.
    PROCEEDINGS OF THE IEEE, 2013, 101 (03) : 676 - 697
  • [23] Discriminative Feature Fusion for Image Classification
    Fernando, Basura
    Fromont, Elisa
    Muselet, Damien
    Sebban, Marc
    2012 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2012, : 3434 - 3441
  • [24] Feature Selection for Image Distortion Classification
    Merrouche, Saad B.
    Bujakovic, Dimitrije M.
    Andric, Milenko S.
    Bondzulic, Boban P.
    2018 14TH SYMPOSIUM ON NEURAL NETWORKS AND APPLICATIONS (NEUREL), 2018,
  • [25] Efficient feature extraction for image classification
    Zhang, Wei
    Xue, Xiangyang
    Sun, Zichen
    Guo, Yue-Fei
    Chi, Mingmin
    Lu, Hong
    2007 IEEE 11TH INTERNATIONAL CONFERENCE ON COMPUTER VISION, VOLS 1-6, 2007, : 1799 - 1806
  • [26] Deep Bottleneck Feature for Image Classification
    Song, Yan
    McloughLin, Ian
    Dai, Lirong
    ICMR'15: PROCEEDINGS OF THE 2015 ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA RETRIEVAL, 2015, : 491 - 494
  • [27] Image representation based PCA feature for image classification
    Ma Zhongli
    Li Qianqian
    Li Huixin
    Ma Zhongli
    Li Zuoyong
    2017 IEEE INTERNATIONAL CONFERENCE ON MECHATRONICS AND AUTOMATION (ICMA), 2017, : 1121 - 1125
  • [28] Recognition and Classification of Wire Bonding Joint via Image Feature and SVM Model
    Long, Zhili
    Zhou, Xing
    Zhang, Xiaobing
    Wang, Rui
    Wu, Xiaojun
    IEEE TRANSACTIONS ON COMPONENTS PACKAGING AND MANUFACTURING TECHNOLOGY, 2019, 9 (05): : 998 - 1006
  • [29] Sparse coding based dense feature representation model for hyperspectral image classification
    Oguslu, Ender
    Zhou, Guoqing
    Zheng, Zezhong
    Iftekharuddin, Khan
    Li, Jiang
    JOURNAL OF ELECTRONIC IMAGING, 2015, 24 (06)
  • [30] Texture image classification based on BoF model with multi-feature fusion
    Wang Y.
    Li M.
    Li J.
    Zhang C.
    Chen H.
    Beijing Hangkong Hangtian Daxue Xuebao/Journal of Beijing University of Aeronautics and Astronautics, 2018, 44 (09): : 1869 - 1877
12345