Abstract
Superpixels have been widely used in computer vision tasks due to their representational and computational efficiency. Meanwhile, deep learning and end-to-end framework have made great progress in various fields including computer vision. However, existing superpixel algorithms cannot be integrated into subsequent tasks in an end-to-end way. Traditional algorithms and deep learning-based algorithms are two main streams in superpixel segmentation. The former is non-differentiable and the latter needs a non-differentiable post-processing step to enforce connectivity, which constraints the integration of superpixels and downstream tasks. In this paper, we propose a deep learning-based superpixel segmentation algorithm SIN which can be integrated with downstream tasks in an end-to-end way. Owing to some downstream tasks such as visual tracking require real-time speed, the speed of generating superpixels is also important. To remove the post-processing step, our algorithm enforces spatial connectivity from the start. Superpixels are initialized by sampled pixels and other pixels are assigned to superpixels through multiple updating steps. Each step consists of a horizontal and a vertical interpolation, which is the key to enforcing spatial connectivity. Multi-layer outputs of a fully convolutional network are utilized to predict association scores for interpolations. Experimental results show that our approach runs at about 80 fps and performs favorably against state-of-the-art methods. Furthermore, we design a simple but effective loss function which reduces much training time. The improvements of superpixel-based tasks demonstrate the effectiveness of our algorithm. We hope SIN will be integrated into downstream tasks in an end-to-end way and benefit the superpixel-based community. Code is available at: https://github.com/yuanqqq/SIN.
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
Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., Süsstrunk, S.: Slic superpixels compared to state-of-the-art superpixel methods. IEEE Trans. Pattern Anal. Mach. Intell. 34(11), 2274–2282 (2012)
Achanta, R., Susstrunk, S.: Superpixels and polygons using simple non-iterative clustering. In: CVPR, pp. 4651–4660, July 2017
Arbelaez, P., Maire, M., Fowlkes, C., Malik, J.: Contour detection and hierarchical image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 33(5), 898–916 (2010)
Van den Bergh, M., Boix, X., Roig, G., de Capitani, B., Van Gool, L.: SEEDS: superpixels extracted via energy-driven sampling. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7578, pp. 13–26. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-33786-4_2
Everingham, M., Eslami, S.A., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes challenge: a retrospective. Int. J. Comput. Vision 111(1), 98–136 (2015)
Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient graph-based image segmentation. Int. J. Comput. Vision 59(2), 167–181 (2004)
Gadde, R., Jampani, V., Kiefel, M., Kappler, D., Gehler, P.V.: Superpixel convolutional networks using bilateral inceptions. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 597–613. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46448-0_36
Gould, S., Rodgers, J., Cohen, D., Elidan, G., Koller, D.: Multi-class segmentation with relative location prior. Int. J. Comput. Vision 80(3), 300–316 (2008)
He, S., Lau, R.W., Liu, W., Huang, Z., Yang, Q.: SuperCNN: a superpixelwise convolutional neural network for salient object detection. Int. J. Comput. Vision 115(3), 330–344 (2015)
Jampani, V., Sun, D., Liu, M.-Y., Yang, M.-H., Kautz, J.: Superpixel sampling networks. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 363–380. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01234-2_22
Li, Z., Chen, J.: Superpixel segmentation using linear spectral clustering. In: CVPR, pp. 1356–1363 (2015)
Liang-Chieh, C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.: Semantic image segmentation with deep convolutional nets and fully connected CRFs. In: ICLR (2015)
Liu, M.Y., Tuzel, O., Ramalingam, S., Chellappa, R.: Entropy rate superpixel segmentation. In: CVPR, pp. 2097–2104. IEEE (2011)
Liu, Y.J., Yu, C.C., Yu, M.J., He, Y.: Manifold slic: a fast method to compute content-sensitive superpixels. In: CVPR, pp. 651–659 (2016)
Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: CVPR, pp. 3431–3440 (2015)
Ren, M.: Learning a classification model for segmentation. In: ICCV, pp. 10–17, vol. 1 (2003). https://doi.org/10.1109/ICCV.2003.1238308
Ren, C.Y., Reid, I.: gSLIC: a real-time implementation of slic superpixel segmentation. University of Oxford, Department of Engineering, Technical report, pp. 1–6 (2011)
Sharma, A., Tuzel, O., Liu, M.Y.: Recursive context propagation network for semantic scene labeling. In: NeurIPS, pp. 2447–2455 (2014)
Shi, J., Yan, Q., Xu, L., Jia, J.: Hierarchical image saliency detection on extended CSSD. IEEE Trans. Pattern Anal. Mach. Intell. 38(4), 717–729 (2015)
Shu, G., Dehghan, A., Shah, M.: Improving an object detector and extracting regions using superpixels. In: CVPR, pp. 3721–3727 (2013)
Silberman, N., Hoiem, D., Kohli, P., Fergus, R.: Indoor segmentation and support inference from RGBD images. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7576, pp. 746–760. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-33715-4_54
Stutz, D., Hermans, A., Leibe, B.: Superpixels: an evaluation of the state-of-the-art. Comput. Vis. Image Underst. 166, 1–27 (2018)
Tu, W.C., et al.: Learning superpixels with segmentation-aware affinity loss. In: CVPR, pp. 568–576 (2018)
Wang, S., Lu, H., Yang, F., Yang, M.H.: Superpixel tracking. In: ICCV, pp. 1323–1330. IEEE (2011)
Yan, J., Yu, Y., Zhu, X., Lei, Z., Li, S.Z.: Object detection by labeling superpixels. In: CVPR, pp. 5107–5116 (2015)
Yang, C., Zhang, L., Lu, H., Ruan, X., Yang, M.H.: Saliency detection via graph-based manifold ranking. In: CVPR, pp. 3166–3173 (2013)
Yang, F., Lu, H., Yang, M.H.: Robust superpixel tracking. IEEE Trans. Image Process. 23(4), 1639–1651 (2014)
Yang, F., Sun, Q., Jin, H., Zhou, Z.: Superpixel segmentation with fully convolutional networks. In: CVPR, pp. 13964–13973 (2020)
Zhu, W., Liang, S., Wei, Y., Sun, J.: Saliency optimization from robust background detection. In: CVPR, pp. 2814–2821 (2014)
Acknowledgments
This work is supported by the Hubei Provincinal Science and Technology Major Project of China under Grant No. 2020AEA011, the Key Research & Development Plan of Hubei Province of China under Grant No. 2020BAB100, the project of Science, Technology and Innovation Commission of Shenzhen Municipality of China under Grant No. JCYJ20210324120002006 and the Fundamental Research Funds for the Central Universities, HUST: 2020JYCXJJ067.
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
Yuan, Q., Lu, S., Huang, Y., Sha, W. (2021). SIN: Superpixel Interpolation Network. In: Pham, D.N., Theeramunkong, T., Governatori, G., Liu, F. (eds) PRICAI 2021: Trends in Artificial Intelligence. PRICAI 2021. Lecture Notes in Computer Science(), vol 13033. Springer, Cham. https://doi.org/10.1007/978-3-030-89370-5_22
Download citation
DOI: https://doi.org/10.1007/978-3-030-89370-5_22
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-89369-9
Online ISBN: 978-3-030-89370-5
eBook Packages: Computer ScienceComputer Science (R0)