Abstract
Recently, Convolution Neural Networks (CNNs) have achieved great success in computer vision. To further boost the performance, the depth of the backbone network is continuously increased, which improves the capacity of feature learning but also brings the heavy burden in computation. To address the issues, this paper introduces a complex convolution method to systematically improve the performance of the backbone network. Our contributions are three-fold: 1) the complex architecture backbone network can improve the classification performance without increasing or even reducing the number of parameters; 2) for the detection task, the complex architecture backbone network can improve the ability of feature map extraction, at the same time our joint bounding box generation method using both real and imaginary parts of complex features can obviously improve the object detection ability. 3) the proposed method has a strong generalization ability for both detection and classification tasks. We have achieved significant performance improvements in both classification and detection tasks, which validate the effectiveness of our methods.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Jiao, L., Zhang, F., Liu, F., et al.: A survey of deep learning-based object detection. IEEE Access 7, 128837–128868 (2019)
Hu, Y., Yang, Y., Zhang, J., et al.: Attentional kernel encoding networks for fine-grained visual categorization. IEEE Trans. Circ. Syst. Video Technol. (2020)
He, K., Zhang, X., Ren, S., Sun, J.: Identity mappings in deep residual networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 630–645. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46493-0_38
He, K., Zhang, X., Ren, S., et al.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
He, K., Gkioxari, G., Dollár, P., et al.: Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961–2969 (2017)
Xie, S., Girshick, R., Dollár, P., et al.: Aggregated residual transformations for deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1492–1500 (2017)
Gao, S., Cheng, M.M., Zhao, K., et al.: Res2net: a new multi-scale backbone architecture. IEEE Trans. Pattern Anal. Mach. Intell. (2019)
Chen, J., Ran, X.: Deep learning with edge computing: a review. Proc. IEEE 107(8), 1655–1674 (2019)
Howard, A.G., Zhu, M., Chen, B., et al.: Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)
Zhang, X., Zhou, X., Lin, M., et al.: Shufflenet: an extremely efficient convolutional neural network for mobile devices. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6848–6856 (2018)
Iandola, F.N., Han, S., Moskewicz, M.W., et al.: SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and < 0.5 MB model size. arXiv preprint arXiv:1602.07360 (2016)
Trabelsi, C., Bilaniuk, O., Zhang, Y., et al.: Deep complex networks. arXiv preprint arXiv:1705.09792 (2017)
Choi, H.S., Kim, J.H., Huh, J., et al.: Phase-aware speech enhancement with deep complex U-Net. arXiv preprint arXiv:1903.03107 (2019)
Pfeifenberger, L., Zöhrer, M., Pernkopf, F.: Deep complex-valued neural beamformers. In: ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2902–2906. IEEE (2019)
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167 (2015)
Li, Z., Peng, C., Yu, G., et al.: Detnet: a backbone network for object detection. arXiv preprint arXiv:1804.06215 (2018)
Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images. In: Handbook of Systemic Autoimmune Diseases, vol. 1, no. 4 (2009)
Fei-Fei, L., Fergus, R., Perona, P.: Learning generative visual models from few training examples: an incremental bayesian approach tested on 101 object categories. In: 2004 Conference on Computer Vision and Pattern Recognition Workshop, p. 178. IEEE (2004)
Deng, J., Dong, W., Socher, R., et al.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255. IEEE (2009)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)
Huang, G., Liu, Z., Van Der Maaten, L., et al.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700–4708 (2017)
Szegedy, C., Liu, W., Jia, Y., et al.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–9 (2015)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132–7141 (2018)
Luan, S., Chen, C., Zhang, B., et al.: Gabor convolutional networks. IEEE Trans. Image Process. 27(9), 4357–4366 (2018)
Girshick, R., Donahue, J., Darrell, T., et al.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 580–587 (2014)
Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440–1448 (2015)
Ren, S., He, K., Girshick, R., et al.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91–99 (2015)
He, K., Zhang, X., Ren, S., et al.: Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 37(9), 1904–1916 (2015)
Redmon, J., Divvala, S., Girshick, R., et al.: You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779–788 (2016)
Liu, W., et al.: SSD: Single Shot MultiBox Detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21–37. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46448-0_2
Liu, Z., Jiang, Z., Wei, F.: OD-GCN object detection by knowledge graph with GCN. arXiv preprint arXiv:1908.04385 (2019)
Kong, T., Sun, F., Yao, A., et al.: Ron: reverse connection with objectness prior networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5936–5944 (2017)
Bochkovskiy, A., Wang, C.Y., Liao, H.Y.M.: YOLOv4: Optimal Speed and Accuracy of Object Detection. arXiv preprint arXiv:2004.10934 (2020)
Acknowledgement
Baochang Zhang is also with Shenzhen Academy of Aerospace Technology, Shenzhen, China, and he is the corresponding author. He is in part Supported by Shenzhen Science and Technology Program (No. KQTD2016112515134654).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Shao, J., Hu, Y., Liu, Z., Ma, T., Zhang, B. (2020). Improving Backbones Performance by Complex Architectures. In: Peng, Y., et al. Pattern Recognition and Computer Vision. PRCV 2020. Lecture Notes in Computer Science(), vol 12306. Springer, Cham. https://doi.org/10.1007/978-3-030-60639-8_33
Download citation
DOI: https://doi.org/10.1007/978-3-030-60639-8_33
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-60638-1
Online ISBN: 978-3-030-60639-8
eBook Packages: Computer ScienceComputer Science (R0)