Abstract
Deep Learning algorithms based on convolutional neural network (CNN) have achieved huge success in semantic segmentation. However, in these networks, sub-sampling will cause a large loss of image detailed information. In this work, we design a novel method for recovering some of the lost pixels. We use two-dimensional discrete Wavelet Transform (DWT) to extract image boundary detailed information and combine the segmentation result of the convolutional network to recover some of the lost details. We analyze the influence of the algorithm parameters and wavelet function on the final prediction. In our experiments, our algorithm has accuracy improvement compared to the deep network on the PASCAL VOC 2012 dataset.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: CVPR (2015)
Badrinarayanan, V., Kendall, R., Cipolla, R.: SegNet: A deep convolutional encoder-decoder architecture for image segmentation. arXiv preprint arXiv:1511.00561v3 (2016)
Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolution. In: ICLR (2016)
Chen, L., lcchen, L., Papandreou, G.: Sematic image segmentation with deep convolutional nets and fully connected CRFS. In: ICLR (2015)
Chen, L., lcchen, L., Papandreou, G.: Encoder-decoder with atrous separable convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587v3 (2018)
Gonzalez, R.C., Woods, R.E.: Digital image process. Publishing House of Electronics Industry, Beijing (2019)
Chen, L., lcchen, L., Papandreou, G., et al.: Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1802.02611v3 (2017)
Fukushima, K.: Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biol. Cybern. 36(4), 193–202 (1980)
Waibel, A., Hanazawa, T., Hinton, G., et al.: Phoneme recognition using time-delay neural networks. IEEE Trans. Acoust. Speech Signal Process. 37(3), 328–339 (1989)
Ronneberger, O., Fischer, P., Brox, T.: U-net: Convolutional networks for biomedical image segmentation. In: International Conference on Medical image computing and computer-assisted intervention (2015)
Milletari, F., Navab, N., Ahmadi, S.-A.: V-net: Fully convolutional neural networks for volumetric medical image segmentation. In: 2016 Fourth International Conference on 3D Vision (3DV) (2016)
Yuan, Y., Chen, X., Wang, J.: Object-contextual representations for semantic segmentation. arXiv preprint arXiv:1909.11065 (2019)
Minaee, S., Boykov, Y., Porikli, F. et al.: Image segmentation using deep learning: A survey. arXiv preprint arXiv:2001.05566v4 (2020)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. arXiv preprint arXiv:1512.03385v1 (2016)
Qiu, X.: Neural networks and deep learing. China Machine Press, Beijing (2020)
Bottou, L.: Large-scale machine learning with stochastic gradient descent. In: Proceedings of COMPSTAT (2010)
Acknowledgement
This work was supported by Tianjin Key Laboratory of Wireless Mobile Communications and Power Transmission.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Yin, X., Xu, X. (2022). A Method for Improving Accuracy of DeepLabv3+ Semantic Segmentation Model Based on Wavelet Transform. In: Liang, Q., Wang, W., Liu, X., Na, Z., Zhang, B. (eds) Communications, Signal Processing, and Systems. CSPS 2021. Lecture Notes in Electrical Engineering, vol 879. Springer, Singapore. https://doi.org/10.1007/978-981-19-0386-1_39
Download citation
DOI: https://doi.org/10.1007/978-981-19-0386-1_39
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-0385-4
Online ISBN: 978-981-19-0386-1
eBook Packages: EngineeringEngineering (R0)