Multi-Scale CNN for Fine-Grained Image Recognition

被引:25
|
作者
Won, Chee Sun [1 ]
机构
[1] Dongguk Univ, Dept Elect & Elect Engn, Seoul 04620, South Korea
基金
新加坡国家研究基金会;
关键词
Convolutional neural network (CNN); fine-grained image classification; food recognition; image resizing; MODEL;
D O I
10.1109/ACCESS.2020.3005150
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Most conventional fine-grained image recognitions are based on a two-stream model of object-level and part-level CNNs, where the part-level CNN is responsible for learning the object-parts and their spatial relationships. To train the part-level CNN, we first need to separate parts from an object. However, there exist sub-level objects with no distinctive and separable parts. In this paper, a multi-scale CNN with a baseline Object-level and multiple Part-level CNNs is proposed for the fine-grained image recognition with no separable object-parts. The basic idea to train different CNNs of the multi-scale CNNs is to adopt different scales in resizing the training images. That is, the training images are resized such that the entire object appears as much as possible for the Object-level CNN, while only a local part of the object is to be included for the Part-level CNN. This scale-specific image resizing approach requires a scale-controllable parameter in the image resizing process. In this paper, a scale-controllable parameter is introduced for the linear-scaling and random-cropping method. Also, a line-based image resizing method with a scale-controllable parameter is employed for the part-level CNNs. The proposed multi-scale CNN is applied to a food image classification, which belongs to a fine-grained classification problem with no separable object-parts. Experimental results on the public food image datasets show that the classification accuracy improves substantially when the predicted scores of the multi-scale CNN are fused together. This reveals that the object-level and part-level CNNs work harmoniously in differentiating subtle differences of the sub-level objects.
引用
收藏
页码:116663 / 116674
页数:12
相关论文
共 50 条
  • [1] Dual attention guided multi-scale CNN for fine-grained image classification
    Liu, Xiaozhang
    Zhang, Lifeng
    Li, Tao
    Wang, Dejian
    Wang, Zhaojie
    INFORMATION SCIENCES, 2021, 573 : 37 - 45
  • [2] Multi-Scale Image Segmentation Model for Fine-Grained Recognition of Zanthoxylum Rust
    Yang, Fan
    Xu, Jie
    Wei, Haoliang
    Ye, Meng
    Xu, Mingzhu
    Fu, Qiuru
    Ren, Lingfei
    Huang, Zhengwen
    CMC-COMPUTERS MATERIALS & CONTINUA, 2022, 71 (02): : 2963 - 2980
  • [3] ASSOCIATING MULTI-SCALE RECEPTIVE FIELDS FOR FINE-GRAINED RECOGNITION
    Ye, Zihan
    Hu, Fuyuan
    Liu, Yin
    Xia, Zhenping
    Lyu, Fan
    Liu, Pengqing
    2020 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2020, : 1851 - 1855
  • [4] Multi-Scale Fine-Grained Alignments for Image and Sentence Matching
    Li, Wenhui
    Wang, Yan
    Su, Yuting
    Li, Xuanya
    Liu, An-An
    Zhang, Yongdong
    IEEE TRANSACTIONS ON MULTIMEDIA, 2023, 25 : 543 - 556
  • [5] RAMS-Trans: Recurrent Attention Multi-scale Transformer for Fine-grained Image Recognition
    Hu, Yunqing
    Jin, Xuan
    Zhang, Yin
    Hong, Haiwen
    Zhang, Jingfeng
    He, Yuan
    Xue, Hui
    PROCEEDINGS OF THE 29TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, MM 2021, 2021, : 4239 - 4248
  • [6] MSEC: Multi-Scale Erasure and Confusion for fine-grained image classification
    Zhang, Yan
    Sun, Yongsheng
    Wang, Nian
    Gao, Zijian
    Chen, Feng
    Wang, Chenfei
    Tang, Jun
    NEUROCOMPUTING, 2021, 449 : 1 - 14
  • [7] Fine-Grained Image Classification Based on Multi-Scale Feature Fusion
    Li Siyao
    Liu Yuhong
    Zhang Rongfen
    LASER & OPTOELECTRONICS PROGRESS, 2020, 57 (12)
  • [8] LEARNING REPRESENTATION OF MULTI-SCALE OBJECT FOR FINE-GRAINED IMAGE RETRIEVAL
    Sun, Kangbo
    Zhu, Jie
    2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021), 2021, : 1660 - 1664
  • [9] Fine-Grained Image Classification Combining Swin and Multi-Scale Feature Fusion
    Xiang, Jianwen
    Chen, Minrong
    Yang, Baibing
    Computer Engineering and Applications, 2023, 59 (20): : 147 - 157
  • [10] Multi-Scale Feature Transformer Based Fine-Grained Image Classification Method
    Zhang T.
    Cai C.
    Luo X.
    Zhu Y.
    Beijing Youdian Daxue Xuebao/Journal of Beijing University of Posts and Telecommunications, 2023, 46 (04): : 70 - 75