Abstract
We propose a lightweight, single-image super-resolution mobile device network named XCAT, and introduce Heterogeneous Group Convolution Blocks with Cross Concatenations (HXBlock). The heterogeneous split of the input channels to the group convolution blocks reduces the number of operations, and cross concatenation allows for information flow between the intermediate input tensors of cascaded HXBlocks. Cross concatenations inside HXBlocks can also avoid using more expensive operations like 1 \(\times \) 1 convolutions. To further prevent expensive tensor copy operations, XCAT utilizes non-trainable convolution kernels to apply upsampling operations. Designed with integer quantization in mind, XCAT also utilizes several techniques in training, like intensity-based data augmentation. Integer quantized XCAT operates in real-time on Mali-G71 MP2 GPU with 320 ms, and on Synaptics Dolphin NPU with 30 ms (NCHW) and 8.8 ms (NHWC), suitable for real-time applications.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ahn, N., Kang, B., Sohn, K.: Fast, accurate, and lightweight super-resolution with cascading residual network. CoRR abs/1803.08664 (2018)
Ayazoglu, M.: Extremely lightweight quantization robust real-time single-image super resolution for mobile devices. CoRR abs/2105.10288 (2021)
Ayazoglu, M.: Imdeception: grouped information distilling super-resolution network (2022)
Cogswell, M., Ahmed, F., Girshick, R., Zitnick, L., Batra, D.: Reducing overfitting in deep networks by decorrelating representations (2015)
Courbariaux, M., Bengio, Y., David, J.P.: Training deep neural networks with low precision multiplications (2015)
Dong, C., Loy, C.C., He, K., Tang, X.: Learning a deep convolutional network for image super-resolution. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8692, pp. 184–199. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10593-2_13
Dong, C., Loy, C.C., He, K., Tang, X.: Learning a deep convolutional network for image super-resolution. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8692, pp. 184–199. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10593-2_13
Du, Z., Liu, J., Tang, J., Wu, G.: Anchor-based plain net for mobile image super-resolution (2021)
Glasner, D., Bagon, S., Irani, M.: Super-resolution from a single image. In: 2009 IEEE 12th International Conference on Computer Vision, pp. 349–356 (2009)
He, Y., Zhang, X., Sun, J.: Channel pruning for accelerating very deep neural networks. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 1398–1406 (2017)
Hui, Z., Gao, X., Yang, Y., Wang, X.: Lightweight image super-resolution with information multi-distillation network, pp. 2024–2032 (2019)
Hui, Z., Wang, X., Gao, X.: Fast and accurate single image super-resolution via information distillation network, pp. 723–731 (2018)
Ignatov, A., et al.: Real-time quantized image super-resolution on mobile NPUs, mobile AI 2021 challenge: Report, pp. 2525–2534 (2021)
Ignatov, A., Timofte, R., Denna, M., Younes, A., et al.: Efficient and accurate quantized image super-resolution on mobile NPUs, mobile AI & aim 2022 challenge: report. In: Proceedings of the European Conference on Computer Vision (ECCV) Workshops (2022)
Ignatov, A., et al.: AI benchmark: all about deep learning on smartphones in 2019 (2019)
Ioannou, Y., Robertson, D., Cipolla, R., Criminisi, A.: Deep roots: Improving CNN efficiency with hierarchical filter groups (2017)
Jacob, B., et al.: Quantization and training of neural networks for efficient integer-arithmetic-only inference, pp. 2704–2713 (2018)
Jain, V., Bansal, P., Kumar Singh, A., Srivastava, R.: Efficient single image super resolution using enhanced learned group convolutions (2018)
Kim, J., Lee, J.K., Lee, K.M.: Accurate image super-resolution using very deep convolutional networks. CoRR abs/1511.04587 (2015)
Kim, J., Lee, J.K., Lee, K.M.: Deeply-recursive convolutional network for image super-resolution. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1637–1645 (2016)
Krishnamoorthi, R.: Quantizing deep convolutional networks for efficient inference: a whitepaper (2018)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Pereira, F., Burges, C., Bottou, L., Weinberger, K. (eds.) Advances in Neural Information Processing Systems, vol. 25. Curran Associates, Inc. (2012)
Ledig, C., et al.: Photo-realistic single image super-resolution using a generative adversarial network. CoRR abs/1609.04802 (2016)
Li, Y., Zhang, K., Timofte, R., Van Gool, L., Kong, E.A.: NTIRE 2022 challenge on efficient super-resolution: methods and results (2022)
Lim, B., Son, S., Kim, H., Nah, S., Lee, K.M.: Enhanced deep residual networks for single image super-resolution. CoRR abs/1707.02921 (2017)
Lin, M., Chen, Q., Yan, S.: Network in network (2013)
Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows (2021)
Niu, B., et al.: Single image super-resolution via a holistic attention network (2020)
Schwarz Schuler, J.P., Romaní, S., Abdel-nasser, M., Rashwan, H., Puig, D.: Grouped pointwise convolutions reduce parameters in convolutional neural networks. Mendel 28, 23–31 (2022)
Shi, W., et al.: Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1874–1883 (2016)
Tai, Y., Yang, J., Liu, X.: Image super-resolution via deep recursive residual network. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2790–2798 (2017)
Vanhoucke, V., Senior, A., Mao, M.: Improving the speed of neural networks on CPUs (2011)
Wang, X., et al.: ESRGAN: enhanced super-resolution generative adversarial networks (2018)
Xie, S., Girshick, R., Dollár, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5987–5995 (2017)
Xu, S., Huang, A., Chen, L., Zhang, B.: Convolutional neural network pruning: a survey. In: 2020 39th Chinese Control Conference (CCC), pp. 7458–7463 (2020)
Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions (2016)
Yu, J., et al.: Wide activation for efficient and accurate image super-resolution. CoRR abs/1808.08718 (2018)
Zhang, T., Qi, G.J., Xiao, B., Wang, J.: Interleaved group convolutions. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 4383–4392 (2017)
Zhang, X., Zhou, X., Lin, M., Sun, J.: ShuffleNet: an extremely efficient convolutional neural network for mobile devices. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6848–6856 (2018)
Zhang, Z., Wang, X., Jung, C.: DCSR: dilated convolutions for single image super-resolution. IEEE Trans. Image Process. 28(4), 1625–1635 (2019)
Zhao, R., Hu, Y., Dotzel, J., De Sa, C., Zhang, Z.: Building efficient deep neural networks with unitary group convolutions, pp. 11295–11304 (2019)
Zoph, B., Vasudevan, V., Shlens, J., Le, Q.V.: Learning transferable architectures for scalable image recognition. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8697–8710 (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Ayazoglu, M., Bilecen, B.B. (2023). XCAT - Lightweight Quantized Single Image Super-Resolution Using Heterogeneous Group Convolutions and Cross Concatenation. In: Karlinsky, L., Michaeli, T., Nishino, K. (eds) Computer Vision – ECCV 2022 Workshops. ECCV 2022. Lecture Notes in Computer Science, vol 13802. Springer, Cham. https://doi.org/10.1007/978-3-031-25063-7_29
Download citation
DOI: https://doi.org/10.1007/978-3-031-25063-7_29
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-25062-0
Online ISBN: 978-3-031-25063-7
eBook Packages: Computer ScienceComputer Science (R0)