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
  • [41] Knowledge Distillation with Feature Maps for Image Classification
    Chen, Wei-Chun
    Chang, Chia-Che
    Lee, Che-Rung
    COMPUTER VISION - ACCV 2018, PT III, 2019, 11363 : 200 - 215
  • [42] Flexible unsupervised feature extraction for image classification
    Liu, Yang
    Nie, Feiping
    Gao, Quanxue
    Gao, Xinbo
    Han, Jungong
    Shao, Ling
    NEURAL NETWORKS, 2019, 115 : 65 - 71
  • [43] Image classification using Principal Feature Analysis
    Khayat, Omid
    Shahdoosti, Hamid Reza
    Khosravi, Mohammad Hosein
    ADVANCES ON ARTIFICIAL INTELLIGENCE, KNOWLEDGE ENGINEERING AND DATA BASES, PROCEEDINGS, 2008, : 198 - +
  • [44] Perceptual feature selection for semantic image classification
    Depalov, Dejan
    Pappas, Thrasyvoulos N.
    Li, Dongge
    Gandhi, Bhavan
    2006 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, ICIP 2006, PROCEEDINGS, 2006, : 2921 - +
  • [45] Combining Multiple Feature for texture image classification
    Yang, Ting
    Shi, Guohua
    Yang, Na
    Wang, Lirong
    2017 10TH INTERNATIONAL CONGRESS ON IMAGE AND SIGNAL PROCESSING, BIOMEDICAL ENGINEERING AND INFORMATICS (CISP-BMEI), 2017,
  • [46] An efficient feature fusion in HSI image classification
    Srivastava, Vishal
    Biswas, Bhaskar
    MULTIDIMENSIONAL SYSTEMS AND SIGNAL PROCESSING, 2020, 31 (01) : 221 - 247
  • [47] Deep feature augmentation for occluded image classification
    Cen, Feng
    Zhao, Xiaoyu
    Li, Wuzhuang
    Wang, Guanghui
    PATTERN RECOGNITION, 2021, 111
  • [48] Multipath feature recalibration DenseNet for image classification
    Bolin Chen
    Tiesong Zhao
    Jiahui Liu
    Liqun Lin
    International Journal of Machine Learning and Cybernetics, 2021, 12 : 651 - 660
  • [49] Historical Land Use as a Feature for Image Classification
    Recio, J. A.
    Hermosilla, T.
    Ruiz, L. A.
    Fernandez-Sarria, A.
    PHOTOGRAMMETRIC ENGINEERING AND REMOTE SENSING, 2011, 77 (04): : 377 - 387
  • [50] DESCRIPTIVE LOCAL FEATURE GROUPS FOR IMAGE CLASSIFICATION
    Yu, Lei
    Liu, Jing
    Xu, Changsheng
    2011 18TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2011,
12345