A Self-Supervised Tree-Structured Framework for Fine-Grained Classification
Source abstract
Abstract
In computer vision, fine-grained classification has become an important issue in recognizing objects with slight visual differences. Usually, it is challenging to generate good performance when solving fine-grained classification problems using traditional convolutional neural networks. To improve the accuracy and training time of convolutional neural networks in solving fine-grained classification problems, this paper proposes a tree-structured framework by eliminating the effect of differences between clusters. The contributions of the proposed method include the following three aspects: (1) a self-supervised method that automatically creates a classification tree, eliminating the need for manual labeling; (2) a machine-learning matcher which determines the cluster to which an item belongs, minimizing the impact of inter-cluster variations on classification; and (3) a pruning criterion which filters the tree-structured classifier, retaining only the models with superior classification performance. The experimental evaluation of the proposed tree-structured framework demonstrates its effectiveness in reducing training time and improving the accuracy of fine-grained classification across various datasets in comparison with conventional convolutional neural network models. Specifically, for the CUB 200 2011, FGVC aircraft, and Stanford car datasets, the proposed method achieves a reduction in training time of 32.91%, 35.87%, and 14.48%, and improves the accuracy of fine-grained classification by 1.17%, 2.01%, and 0.59%, respectively.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Neural Network Applications · Industrial Vision Systems and Defect Detection · Domain Adaptation and Few-Shot Learning
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Central China Normal University Wollongong Joint Institute, Faculty of Artificial Intelligence in Education, Central China Normal University, Wuhan 430079, China
Funding
National Natural Science Foundation of China · Central China Normal University (CCNU)
References (34)
Show source-provided references
1. Feature refinement and filter network for person re-identification10.1109/TCSVT.2020.3043026 ↗
2. P-CNN: Part-based convolutional neural networks for fine-grained visual categorization10.1109/TPAMI.2019.2933510 ↗
3. Fine-grained 3D shape classification with hierarchical part-view attention10.1109/TIP.2020.3048623 ↗
4. Lin, D., Shen, X., Lu, C., and Jia, J. (2015, January 7–15). Deep lac: Deep localization, alignment and classification for fine-grained recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.10.1109/CVPR.2015.7298775 ↗
5. Deep cnns meet global covariance pooling: Better representation and generalization
6. Lu, Z., and Yang, Z. (2021, January 4–6). Image recognition based on improved recurrent attention network. Proceedings of the 2021 4th International Conference on Robotics, Control and Automation Engineering (RCAE), Wuhan, China.10.1109/RCAE53607.2021.9638911 ↗
7. Comprehensive assessment of fine-grained wound images using a patch-based CNN with context-preserving attention10.1109/OJEMB.2021.3092207 ↗
8. Selective convolutional descriptor aggregation for fine-grained image retrieval10.1109/TIP.2017.2688133 ↗
9. Zhang, F., Li, M., Zhai, G., and Liu, Y. (2021, January 22–24). Multi-branch and multi-scale attention learning for fine-grained visual categorization. Proceedings of the MultiMedia Modeling: 27th International Conference, MMM 2021, Part I 27, Prague, Czech Republic.10.1007/978-3-030-67832-6_12 ↗
10. Breiki, F.A., Ridzuan, M., and Grandhe, R. (2021). Self-supervised learning for fine-grained image classification. arXiv.
11. Improving classification with semi-supervised and fine-grained learning10.1016/j.patcog.2018.12.002 ↗
12. Weakly supervised fine-grained categorization with part-based image representation10.1109/TIP.2016.2531289 ↗
13. DenseNet-201-based deep neural network with composite learning factor and precomputation for multiple sclerosis classification
14. Deep CNNs with spatially weighted pooling for fine-grained car recognition10.1109/TITS.2017.2679114 ↗
15. Tanno, R., Arulkumaran, K., Alexander, D., Criminisi, A., and Nori, A. (2019, January 9–15). Adaptive neural trees. Proceedings of the International Conference on Machine Learning, PMLR, Long Beach, CA, USA.
16. Chien, E., Chang, W.C., Hsieh, C.J., Yu, H.F., Zhang, J., Milenkovic, O., and Dhillon, I.S. (2021). Node feature extraction by self-supervised multi-scale neighborhood prediction. arXiv.
17. Daumé, H., Karampatziakis, N., Langford, J., and Mineiro, P. (2017, January 6–11). Logarithmic time one-against-some. Proceedings of the International Conference on Machine Learning, Sydney, Australia. PMLR.
18. Morin, F., and Bengio, Y. (2005, January 6–8). Hierarchical probabilistic neural network language model. Proceedings of the International Workshop on Artificial Intelligence and Statistics, PMLR, Barbados, Caribbean.
19. Baharav, T.Z., Jiang, D.L., Kolluri, K., Sanghavi, S., and Dhillon, I.S. (2021, January 1–5). Enabling efficiency-precision trade-offs for label trees in extreme classification. Proceedings of the 30th ACM International Conference on Information & Knowledge Management, Online.10.1145/3459637.3481914 ↗
20. Yu, H.F., Zhang, J., Chang, W.C., Jiang, J.Y., Li, W., and Hsieh, C.J. (2022, January 14–18). Pecos: Prediction for enormous and correlated output spaces. Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Washington, DC, USA.10.1145/3534678.3542629 ↗
21. A computational approach towards visual object recognition at taxonomic levels of concepts
22. Hierarchical metric learning for optical remote sensing scene categorization10.1109/LGRS.2018.2884675 ↗
23. TMTCPT: The Tree Method based on the Taxonomic Categorization and the Phylogenetic Tree for fine-grained categorization10.1016/j.biosystems.2020.104137 ↗
24. Hasan, M.S. (2017, January 22–24). An application of pre-trained CNN for image classification. Proceedings of the 2017 20th International Conference of Computer and Information Technology (ICCIT), Dhaka, Bangladesh.
25. Using sst/macro for effective analysis of mpi-based applications: Evaluating large-scale genomic sequence search10.1109/ACCESS.2013.2272434 ↗
26. He, K., Zhang, X., Ren, S., and Sun, J. (July, January 26). Deep residual learning for image recognition. Proceedings of the IEEE Conference on CComputer Vision and Pattern Recognition, Las Vegas, NV, USA.
27. Arthur, D., and Vassilvitskii, S. (2006). k-Means++: The Advantages of Careful Seeding, Stanford University. Technical Report.
28. Maji, S., Rahtu, E., Kannala, J., Blaschko, M., and Vedaldi, A. (2013). Fine-grained visual classification of aircraft. arXiv.
29. Wah, C., Branson, S., Welinder, P., Perona, P., and Belongie, S. (2011). The Caltech-Ucsd Birds-200-2011 Dataset, California Institute of Technology.
30. Krause, J., Stark, M., Deng, J., and Fei-Fei, L. (2013, January 2–8). 3d object representations for fine-grained categorization. Proceedings of the IEEE International Conference on Computer Vision Workshops, Washington, DC, USA.10.1109/ICCVW.2013.77 ↗
31. Bora, M., Jyoti, D., Gupta, D., and Kumar, A. (2014). Effect of different distance measures on the performance of K-means algorithm: An experimental study in Matlab. arXiv.
32. Two theorems in graph theory10.1073/pnas.43.9.842 ↗
33. Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z. (2016, January 27–30). Rethinking the inception architecture for computer vision. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.308 ↗
34. Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., and Adam, H. (2017). Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv.