Abstract
Fine-grained visual classification (FGVC) is a fundamental and longstanding problem aiming to recognize objects belonging to different subclasses accurately. Unfortunately, since categories are often confused, this task is genuinely challenging. Most previous methods solve this problem in two main ways: adding more annotations or constructing more complex structures. These approaches, however, require expensive labels or sophisticated designs. To alleviate these constraints, in this work, we propose an easy but efficient method called DA-ViT, just using data augmentations to supervise the model. Specifically, we adopt a vision transformer as the backbone. Then, we introduce highly interpretable visual heatmaps to guide the targeted data augmentations, and three methods (local area enlargement, flipping, and cutout) are created based on the high-response areas. Furthermore, the margins among confusing classes can be increased by simply using label smoothing. Extensive experiments conducted on three popular fine-grained benchmarks demonstrate that we achieve SOTA performance. Meanwhile, during the inference, our method requires less computational burden.
This work is supported by the National Natural Science Foundation of China, Research on Key Technologies of Highly Reliable Nodes in Darknet Communication, no. 62162060.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Chefer, H., Gur, S., Wolf, L.: Transformer interpretability beyond attention visualization. arXiv:2012.09838 (2020)
Chen, Y., Bai, Y.L., Zhang, W., Mei, T.: Destruction and construction learning for fine-grained image recognition. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5152–5161 (2019). https://doi.org/10.1109/CVPR.2019.00530
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Houlsby, N.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv:2010.11929 (2021)
Dubey, A., Gupta, o., Raskar, R., Naik, N.: Maximum-entropy fine-grained classification. arXiv:1809.05934 (2018)
Gao, Y., Han, X., Wang, X., Huang, W., Scott, M.: Channel interaction networks for fine-grained image categorization. arXiv:2003.05235 (2020)
Guo, P., Farrell, R.: Aligned to the object, not to the image: a unified pose-aligned representation for fine-grained recognition. arXiv:1801.09057v4 (2018)
He, J., et al.: Transfg: a transformer architecture for fine-grained recognition. arXiv:2103.07976 (2021)
He, X.T., Peng, Y.X., Zhao, J.J., et al.: Which and how many regions to gaze: focus discriminative regions for fine-grained visual categorization. Int. J. Comput. Vision 127(9), 1235–1255 (2019). https://doi.org/10.1007/s11263-019-01176-2
Horn, G.V., Branson, S., Farrell, R., Haber, S., Belongie, S.: Building a bird recognition app and large scale dataset with citizen scientists: the fine print in fine-grained dataset collection. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 595–604 (2015). https://doi.org/10.1109/CVPR.2015.7298658
Hu, Y., et al.: Rams-trans: recurrent attention multi-scale transformer for fine-grained image recognition. arXiv:2107.08192 (2021)
Khosla, A., Jayadevaprakash, N., Yao, B., Li, F.F.: Novel dataset for fine-grained image categorization. In: IEEE Conference on Computer Vision and Pattern Recognition (2013)
Lin, T.Y., Roychowdhury, A., Maji, S.: Bilinear cnn models for fine-grained visual recognition. arXiv:1504.07889 (2015)
Liu, X., Wang, L., Han, X.: Transformer with peak suppression and knowledge guidance for fine-grained image recognition. arXiv:2107.06538 (2021)
Luo, W., et al.: Cross-x learning for fine-grained visual categorization. arXiv:1909.04412v1 (2019)
Tao, H., Qi, H.: See better before looking closer: weakly supervised data augmentation network for fine-grained visual classification. arXiv:1901.09891 (2019)
Touvron, H., Vedaldi, A., Douze, M., Jégou, H.: Fixing the train-test resolution discrepancy. arXiv:1906.06423v3 (2020)
Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The caltech-ucsd birds- 200–2011 dataset. Tech. rep., california institute of technology (2011)
Wang, J., Yu, X., Gao, Y.: Feature fusion vision transformer for fine-grained visual categorizatio. arXiv:2107.02341 (2021)
Wei, X.S., Xie, C.W., Wu, J.X., Shen, C.H.: Mask-cnn: localizing parts and selecting descriptors for fine-grained bird species categorization. Pattern Recogn. 76, 704–714 (2018). https://doi.org/10.1016/j.patcog.2017.10.002
Zhang, N., Donahue, J., Girshick, R., Darrell, T.: Part-based R-CNNs for fine-grained category detection. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 834–849. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10590-1_54
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Yuan, S., Guo, W., Han, F. (2023). A Data Augmentation Based ViT for Fine-Grained Visual Classification. In: Iliadis, L., Papaleonidas, A., Angelov, P., Jayne, C. (eds) Artificial Neural Networks and Machine Learning – ICANN 2023. ICANN 2023. Lecture Notes in Computer Science, vol 14255. Springer, Cham. https://doi.org/10.1007/978-3-031-44210-0_1
Download citation
DOI: https://doi.org/10.1007/978-3-031-44210-0_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-44209-4
Online ISBN: 978-3-031-44210-0
eBook Packages: Computer ScienceComputer Science (R0)