Abstract
Imbalance visual regression is an important and challenging task, and research on it is still in its early stages. Among the existing solutions, either additional calibration layers need to be added to calibrate the label distribution or feature distribution of the imbalanced data, or a multi-stage training method with a loss function is used to mitigate the imbalance of the data, all of which cause significant time loss. In this paper, we propose an end-to-end multi-branch dynamic residual fusion network (MBDRFN) for imbalance visual regression. MBDRFN consists of a multi-branch residual fusion module (MBRF) and a dynamic balance factor (DBF) that works in concert to overcome the challenge of imbalanced visual regression. The MBRF module has three specialized branches corresponding to three magnitudes of sample labels, and can optimize each branch in a targeted manner to ensure overall fitting performance. The DBF builds on the MBRF and guides the model to gradually focus on learning and optimizing rare sample labels during the training process. Then, we use residual fusion to aggregate the loss functions of dedicated and master branches. The proposed MBDRFN method not only ensures that the model performs well on frequent and regular sample labels, but also improves its performance on rare sample labels with no significant time loss. Finally, we conduct extensive experiments on two real-world datasets to demonstrate the effectiveness and superiority of the proposed MBDRFN method.
Z. Huang and D. Cheng—Equal contribution.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Bengio, Y., Lecun, Y., Hinton, G.: Deep learning for AI. Commun. ACM 64(7), 58–65 (2021)
Branco, P., Torgo, L., Ribeiro, R.P.: SMOGN: a pre-processing approach for imbalanced regression. In: First International Workshop on Learning with Imbalanced Domains: Theory and Applications, pp. 36–50. PMLR (2017)
Cao, D., Zhu, X., et al.: Domain balancing: face recognition on long-tailed domains. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5671–5679 (2020)
Cao, K., Wei, C., et al.: Learning imbalanced datasets with label-distribution-aware margin loss. In: Advances in Neural Information Processing Systems, vol. 32 (2019)
Cui, J., Liu, S., et al.: Reslt: residual learning for long-tailed recognition. IEEE Trans. Pattern Anal. Mach. Intell. (2022)
He, K., Zhang, X., et al.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Hu, R., Cheng, D., et al.: Low-rank feature selection for multi-view regression. Multimedia Tools Appl. 76, 17479–17495 (2017)
Kang, B., Li, Y., et al.: Exploring balanced feature spaces for representation learning. In: International Conference on Learning Representations (2021)
Kang, B., Xie, S., et al.: Decoupling representation and classifier for long-tailed recognition. arXiv preprint arXiv:1910.09217 (2019)
Liang, R., Zhang, G., et al.: Bilateral-branch network for imbalanced visual regression. In: 2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI), pp. 140–147. IEEE (2022)
Lin, T.Y., Goyal, P., et al.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980–2988 (2017)
Liu, Z., Miao, Z., et al.: Large-scale long-tailed recognition in an open world. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2537–2546 (2019)
Ma, Y., Tian, Y., et al.: Class-imbalanced learning on graphs: a survey. arXiv preprint arXiv:2304.04300 (2023)
Menon, A.K., Jayasumana, S., et al.: Long-tail learning via logit adjustment. arXiv preprint arXiv:2007.07314 (2020)
Moschoglou, S., Papaioannou, A., et al.: AgeDB: the first manually collected, in-the-wild age database. In: proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. pp. 51–59 (2017)
Punyani, P., Gupta, R., Kumar, A.: Neural networks for facial age estimation: a survey on recent advances. Artif. Intell. Rev. 53, 3299–3347 (2020)
Ren, J., Zhang, M., et al.: Balanced MSE for imbalanced visual regression. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7926–7935 (2022)
Rothe, R., Timofte, R., Van Gool, L.: Deep expectation of real and apparent age from a single image without facial landmarks. Int. J. Comput. Vision 126(2–4), 144–157 (2018)
Steininger, M., Kobs, K., et al.: Density-based weighting for imbalanced regression. Mach. Learn. 110, 2187–2211 (2021)
Stocksieker, S., Pommeret, D., Charpentier, A.: Data augmentation for imbalanced regression. arXiv preprint arXiv:2302.09288 (2023)
Tan, J., Wang, C., et al.: Equalization loss for long-tailed object recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 11662–11671 (2020)
Tian, H., Tian, C., et al.: Unbalanced regression sample generation algorithm based on confrontation. Inf. Sci. 119157 (2023)
Torgo, L., Ribeiro, R.P., Pfahringer, B., Branco, P.: SMOTE for regression. In: Correia, L., Reis, L.P., Cascalho, J. (eds.) EPIA 2013. LNCS (LNAI), vol. 8154, pp. 378–389. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-40669-0_33
Wang, X., Lian, L., et al.: Long-tailed recognition by routing diverse distribution-aware experts. arXiv preprint arXiv:2010.01809 (2020)
Wu, O.: Rethinking class imbalance in machine learning. arXiv preprint arXiv:2305.03900 (2023)
Yang, Y., Xu, Z.: Rethinking the value of labels for improving class-imbalanced learning. In: Advances in Neural Information Processing Systems, vol. 33, pp. 19290–19301 (2020)
Yang, Y., Zha, K., et al.: Delving into deep imbalanced regression. In: International Conference on Machine Learning, pp. 11842–11851. PMLR (2021)
Zha, K.: Deep Imbalanced Regression: Challenges, Methods, and Applications. Ph.D. thesis, Massachusetts Institute of Technology (2022)
Zhang, K., Lu, G., et al.: Personalized headline generation with enhanced user interest perception. In: Pimenidis, E., Angelov, P., Jayne, C., Papaleonidas, A., Aydin, M. (eds.) ICANN 2022. LNCS, vol. 13530, pp. 797–809. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-15931-2_65
Zhang, S., Cheng, D., et al.: Supervised feature selection algorithm via discriminative ridge regression. World Wide Web 21, 1545–1562 (2018)
Zhang, S., Yang, L., et al.: Leverage triple relational structures via low-rank feature reduction for multi-output regression. Multimedia Tools Appl. 76, 17461–17477 (2017)
Zhang, Y., Kang, B., et al.: Deep long-tailed learning: a survey. IEEE Trans. Pattern Anal. Mach. Intell. (2023)
Acknowledgments
This research was supported in part by the Project of Guangxi Science and Technology (GuiKeAB23026040).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Huang, Z., Zhang, S., Cheng, D., Liang, R., Jiang, M. (2024). Multi-branch Residual Fusion Network for Imbalanced Visual Regression. In: Song, X., Feng, R., Chen, Y., Li, J., Min, G. (eds) Web and Big Data. APWeb-WAIM 2023. Lecture Notes in Computer Science, vol 14331. Springer, Singapore. https://doi.org/10.1007/978-981-97-2303-4_26
Download citation
DOI: https://doi.org/10.1007/978-981-97-2303-4_26
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-97-2302-7
Online ISBN: 978-981-97-2303-4
eBook Packages: Computer ScienceComputer Science (R0)