Abstract
Evidential deep learning (EDL) has been proposed to estimate the uncertainty and the prediction confidence of neural networks. In this paper, we investigate the fusion method based on the EDL model and Dempster’s rule of combination. For fusion models, a better uncertainty estimation may be more helpful than high accuracy. To this end, we propose a deep evidential fusion method to best utilize the belief assignment and uncertainty estimation by improving the objective function and introducing the approximation of the base rate distributions. The experimental results show that our proposed method achieves a more reliable fusion result. We also explore the application of belief function and evidence theory in the field of medical image analysis, where multi-modality well fits the framework of belief functions.
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
Barz, B., Denzler, J.: Deep learning on small datasets without pre-training using cosine loss. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), March 2020
Han, Z., Zhang, C., Fu, H., Zhou, J.T.: Trusted multi-view classification. In: International Conference on Learning Representations (2021)
Hemmer, P., Kühl, N., Schöffer, J.: Deal: deep evidential active learning for image classification. In: 2020 19th IEEE International Conference on Machine Learning and Applications (ICMLA), pp. 865–870 (2020)
Jøsang, A.: Subjective Logic. Artificial Intelligence: Foundations, Theory, and Algorithms, Springer, Cham (2016). https://doi.org/10.1007/978-3-319-42337-1
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Bengio, Y., LeCun, Y. (eds.) 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, 7–9 May 2015, Conference Track Proceedings (2015)
Raghu, M., Zhang, C., Kleinberg, J., Bengio, S.: Transfusion: understanding transfer learning for medical imaging. In: Wallach, H., Larochelle, H., Beygelzimer, A., d’Alché-Buc, F., Fox, E., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 32. Curran Associates, Inc. (2019)
Sensoy, M., Kaplan, L., Kandemir, M.: Evidential deep learning to quantify classification uncertainty. In: Bengio, S., Wallach, H., Larochelle, H., Grauman, K., Cesa-Bianchi, N., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 31. Curran Associates, Inc. (2018)
Shi, Y., Siddharth, N., Paige, B., Torr, P.: Variational mixture-of-experts autoencoders for multi-modal deep generative models. In: Wallach, H., Larochelle, H., Beygelzimer, A., d’Alché-Buc, F., Fox, E., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 32. Curran Associates, Inc. (2019)
Tong, Z., Xu, P., Denœux, T.: An evidential classifier based on Dempster-Shafer theory and deep learning. Neurocomputing 450, 275–293 (2021)
Tsiligkaridis, T.: Failure prediction by confidence estimation of uncertainty-aware Dirichlet networks. CoRR abs/2010.09865 (2020)
Tsiligkaridis, T.: Information aware max-norm Dirichlet networks for predictive uncertainty estimation. Neural Netw. 135, 105–114 (2021)
Acknowledgments
This work was supported by National Natural Science Foundation of China (No. 92046008, 62173252), the Shanghai Innovation Action Project of Science and Technology (No. 20Y11912500), and the Fundamental Research Funds for the Central Universities.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Xu, S., Chen, Y., Ma, C., Yue, X. (2021). Deep Evidential Fusion Network for Image Classification. In: Denœux, T., Lefèvre, E., Liu, Z., Pichon, F. (eds) Belief Functions: Theory and Applications. BELIEF 2021. Lecture Notes in Computer Science(), vol 12915. Springer, Cham. https://doi.org/10.1007/978-3-030-88601-1_19
Download citation
DOI: https://doi.org/10.1007/978-3-030-88601-1_19
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-88600-4
Online ISBN: 978-3-030-88601-1
eBook Packages: Computer ScienceComputer Science (R0)