Fine-grained Image Recognition Method using Discriminative Region-based Data Augmentation

Jingyuan He; Bailong Yang

doi:10.54097/fcis.v1i3.1973

Authors

Jingyuan He
Bailong Yang

DOI:

https://doi.org/10.54097/fcis.v1i3.1973

Keywords:

Fine-grained image recognition, Data augmentation, Attention mechanism, Discriminative region

Abstract

In order to reduce the complexity of the network model and improve the accuracy of image recognition, a fine-grained image recognition method using discriminative region-based data augmentation is proposed. The method obtains the discriminative regions of the image through the attention mechanism, and then performs diversity data augmentation based on the discriminative regions, including region crop, region drop and region mix, and then uses the generated augmented samples to train the network model, the backbone network of the model is ResNet50. The proposed method is tested on 4 commonly used fine-grained image datasets CUB-200-2011, Stanford Cars, FGVC Aircraft and Stanford Dogs, and achieves high accuracy. The experimental results show that the proposed method can improve the localization ability and feature extraction ability of the model for discriminative regions, and it is more lightweight and easier to implement.

Downloads

Download data is not yet available.

References

H. Wei (2021). Analysis and Research of Key Technologies for Fine-grained Image Recognition Based on Convolutional Neural Networks. Changchun Institute of Optics, Fine Mechanics and Physics Chinese Academy of Sciences.

X. X. Zeng (2020). Analysis and Research of Deep Learning based Fine-Grained Feature. Guangdong University of Technology.

C. B. Liu (2021). Research on Key Technologies of Fine-grained Image Recognition. University of Science and Technology of China.

Krizhevsky A, Sutskever I, Hinton G E.Imagenet classification with deep convolutional neural networks[J]// Communications of the ACM, 60(6):84-90,2017.

Cubuk E D, Zoph B, Mane D, et al.Autoaugment: Learning augmentation policies from data[J]. CoRR, 2018, abs/1805.09501.

Zhong Z, Zheng L, Kang G, et al. Random erasing data augmentation[C]// Proceedings of the AAAI Conference on Artificial Intelligence,34(07):13001-13008,2020.

Zhang H, Cisse M, Dauphin Y, Lopez-Paz D. Mixup: Beyond empirical risk minimization[C]// International Conference on Learning Representations, 2018.

YunS, Han D, Chun S, et al. Cutmix: Regularization strategy to train strong classifiers with localizable features[C]// IEEE/CVF International Conference on Computer Vision (ICCV), 2019:6022-6031.

Devries T, Taylor G W. Improved regularization of convolutional neural networks with cutout[J]. CoRR, 2017. abs/1708.04552.

Kim T, Kim H, Byun H. Localization-Aware Adaptive Pairwise MarginLoss for Fine-Grained Image Recognition[J]. IEEE Access, 9:8786-8796,2021.

Hataya R, Zdenek J, Yoshizoe K, et al. Meta Approach to Data Augmentation Optimization[C]// 2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2022, pp. 3535-3544, doi: 10.1109/WACV51458.2022.00359.

Li H,Zhang X, Tian Q,et al. Attribute Mix: Semantic Data Augmentation for Fine Grained Recognition[C]// 2020 IEEE International Conference on Visual Communications and Image Processing (VCIP), 2020, pp. 243-246, doi: 10.1109/VCIP49819.2020.9301763.

He M, Cheng Q, Qi G. Weakly Supervised Semantic and Attentive Data Mixing Augmentation for Fine-Grained Visual Categorization[J]. IEEE Access, 2022,10:35814-35823. doi: 10.1109/ACCESS.2022.3163302.

W. C. Yu (2021). Study of Fine-grained Image Classification Algorithm. Guilin University of Electronic Technology.

Wah C, Branson S, Welinder P, et al. The caltech-ucsd birds-200-2011 dataset[J]. California Institute of Technology, 2011.

Krause J, Stark M, Deng J, et al. 3D object representations for fine-grained categorization[C]// IEEE International Conference on Computer Vision (ICCV), 2013:554-561.

Maji S, Rahtu E, Kannala J, et al. Fine-grained visual classification of aircraft[J], arXiv: Computer Vision and Pattern Recognition, 2013.

Khosla A, Jayadevaprakash N, Yao B, et al. Novel Dataset for Fine-Grained Image Categorization: Stanford Dogs[J]. Computer Science, 2011.

Fu J, Zheng H, Mei T. Look closer to see better: Recurrent attention convolutional neural network for fine-grained image recognition[C]// 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA, July 21-26, 2017. IEEE Computer Society, 2017: 4476-4484.

ZhengH, Fu J, Mei T,et al. Learning multi-attentionconvolutionalneuralnetworkfor fine-grainedimagerecognition[C]// 2017 IEEEInternational ConferenceonComputerVision. ICCV 2017, Venice, Italy, October 22-29, 2017. IEEE Computer Society, 2017:5219-5227.

Sun M, Yuan Y, Zhou F, et al. Multi-Attention Multi-Class Constraint for Fine-grained Image Recognition[C]//Computer Vision-ECCV 2018-15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings, Part XVI.2018:834-850.

Wang Y, Morariu V I, Davis L S. Learning a discriminative filter bank within a CNN for fine-grained recognition[C]// 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018, Salt Lake City, UT, USA, June 18-22, 2018. IEEE Computer Society,2018: 4148-4157.

Yang Z, Luo T, Wang D, et al.Learning to navigate for fine-structure classification[C]// Computer Vision-ECCV 2018-15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings, Part XIV. 2018:438-454.

Hu T, Qi H, Huang Q, et al. See better before looking closer: Weakly supervised data augmentation network for fine-grained visual classification[J]. arXiv: Computer Vision and Pattern Recognition, 2019.