Leveraging local diversity in weakly supervised fine-grained image classification
Abstract
Fine-grained image classification (FGIC) presents a challenge due to the high similarity between visually similar categories, requiring precise feature extraction. Traditional supervised methods demand large amounts of labeled data, which is often unavailable. This paper introduces a local diversity-guided weakly supervised method to address these challenges by leveraging weakly annotated data, thus alleviating the dependence on fully labeled datasets. The approach focuses on fine-grained object recognition by combining local diversity features with weak labels, which significantly improves classification performance. Experimental results on several benchmark datasets demonstrate the method's effectiveness in enhancing the precision of fine-grained classification tasks.
Keywords
Fine-grained image classification, weakly supervised learning, local diversity guidanceHow to Cite
References
Luo, J.; Wu, J. A Survey on Fine-Grained Image Categorization Using Deep Convolutional Features. Acta Autom. Sin. 2017, 43, 1306–1318. [Google Scholar] [CrossRef]
Zhang, N.; Donahue, J.; Girshick, R.; Darrell, T. Part-Based R-CNNs for Fine-Grained Category Detection. In Computer Vision—ECCV 2014; Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T., Eds.; Lecture Notes in Computer Science; Springer International Publishing: Cham, Switzerland, 2014; Volume 8689, pp. 834–849. ISBN 978-3-319-10589-5. [Google Scholar]
Huang, S.; Xu, Z.; Tao, D.; Zhang, Y. Part-Stacked CNN for Fine-Grained Visual Categorization. In Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 27–30 June 2016; IEEE: Las Vegas, NV, USA, 2016; pp. 1173–1182. [Google Scholar]
Xiao, T.; Xu, Y.; Yang, K.; Zhang, J.; Peng, Y.; Zhang, Z. The Application of Two-Level Attention Models in Deep Convolutional Neural Network for Fine-Grained Image Classification. In Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA, 7–12 June 2015; IEEE: Boston, MA, USA, 2015; pp. 842–850. [Google Scholar]
Wang, Z.; Wang, S.; Yang, S.; Li, H.; Li, J.; Li, Z. Weakly Supervised Fine-Grained Image Classification via Guassian Mixture Model Oriented Discriminative Learning. In Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, 14–19 June 2020; IEEE: Seattle, WA, USA, 2020; pp. 9746–9755. [Google Scholar]
Lin, T.-Y.; RoyChowdhury, A.; Maji, S. Bilinear CNN Models for Fine-Grained Visual Recognition. In Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV), Santiago, Chile, 7–13 December 2015; IEEE: Santiago, Chile, 2015; pp. 1449–1457. [Google Scholar]
Peng, Y.; He, X.; Zhao, J. Object-Part Attention Model for Fine-Grained Image Classification. IEEE Trans. Image Process. 2018, 27, 1487–1500. [Google Scholar] [CrossRef]
Rodriguez, P.; Velazquez, D.; Cucurull, G.; Gonfaus, J.M.; Roca, F.X.; Gonzalez, J. Pay Attention to the Activations: A Modular Attention Mechanism for Fine-Grained Image Recognition. IEEE Trans. Multimed. 2020, 22, 502–514. [Google Scholar] [CrossRef]
Zheng, H.; Fu, J.; Zha, Z.-J.; Luo, J. Looking for the Devil in the Details: Learning Trilinear Attention Sampling Network for Fine-Grained Image Recognition. In Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA, 15–20 June 2019; IEEE: Long Beach, CA, USA, 2019; pp. 5007–5016. [Google Scholar]
Ji, R.; Wen, L.; Zhang, L.; Du, D.; Wu, Y.; Zhao, C.; Liu, X.; Huang, F. Attention Convolutional Binary Neural Tree for Fine-Grained Visual Categorization. In Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, 14–19 June 2020; IEEE: Seattle, WA, USA, 2020; pp. 10465–10474. [Google Scholar]
Khosla, A.; Jayadevaprakash, N.; Yao, B.; Li, F.-F. Novel Dataset for Fine-Grained Image Categorization: Stanford Dogs. 2012. Available online: https://people.csail.mit.edu/khosla/papers/fgvc2011.pdf (accessed on 7 November 2024).
Krause, J.; Stark, M.; Deng, J.; Fei-Fei, L. 3D Object Representations for Fine-Grained Categorization. In Proceedings of the 2013 IEEE International Conference on Computer Vision Workshops, Sydney, Australia, 2–8 December 2013; IEEE: Sydney, Australia, 2013; pp. 554–561. [Google Scholar]
Maji, S.; Rahtu, E.; Kannala, J.; Blaschko, M.; Vedaldi, A. Fine-Grained Visual Classification of Aircraft. 2013. Available online: http://arxiv.org/abs/1306.5151 (accessed on 7 November 2024).
Wah, C.; Branson, S.; Welinder, P.; Perona, P.; Belongie, S. Caltech-UCSD Birds-200-2011; California Institute of Technology: Pasadena, CA, USA, 2011. [Google Scholar]
Yang, Z.; Luo, T.; Wang, D.; Hu, Z.; Gao, J.; Wang, L. Learning to Navigate for Fine-Grained Classification. In Computer Vision—ECCV 2018; Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y., Eds.; Lecture Notes in Computer Science; Springer International Publishing: Cham, Switzerland, 2018; Volume 11218, pp. 438–454. ISBN 978-3-030-01263-2. [Google Scholar]
Du, R.; Chang, D.; Bhunia, A.K.; Xie, J.; Ma, Z.; Song, Y.-Z.; Guo, J. Fine-Grained Visual Classification via Progressive Multi-Granularity Training of Jigsaw Patches. In Computer Vision—ECCV 2020; Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M., Eds.; Lecture Notes in Computer Science; Springer International Publishing: Cham, Switzerland, 2020; Volume 12365, pp. 153–168. ISBN 978-3-030-58564-8. [Google Scholar]
Liu, C.; Xie, H.; Zha, Z.-J.; Ma, L.; Yu, L.; Zhang, Y. Filtration and Distillation: Enhancing Region Attention for Fine-Grained Visual Categorization. Proc. AAAI Conf. Artif. Intell. 2020, 34, 11555–11562. [Google Scholar] [CrossRef]
Wang, Z.; Wang, S.; Li, H.; Dou, Z.; Li, J. Graph-Propagation Based Correlation Learning for Weakly Supervised Fine-Grained Image Classification. Proc. AAAI Conf. Artif. Intell. 2020, 34, 12289–12296. [Google Scholar] [CrossRef]
License
Copyright (c) 2025 Antonio Pedro
This work is licensed under a Creative Commons Attribution 4.0 International License.