Abstract
Glass-like object detection aims to detect and segment whole glass objects from complex backgrounds. Due to the transparency of glass, existing detection methods often suffer from blurred object boundaries. Recently, several methods introduce edge information to boost performance. However, glass boundary pixels are extremely sparser than others. Using only edge pixels may negatively affect the glass detection performance due to the unbalanced distribution of edge and non-edge pixels. In this study, we propose a new detail-guided and cross-level fusion network (which we call DCNet) to tackle the issues of glass-like object detection. Firstly, we exploit label decoupling to get detail labels and propose a multi-scale detail interaction module (MDIM) to explore finer detail cues. Secondly, we design a body-induced cross-level fusion module (BCFM), which effectively guides the integration of features at different levels and leverages discontinuities and correlations to refine the glass boundary. Finally, we design an attention-induced aggregation module (AGM) that can effectively mine local pixel and global semantic cues from glass-like object regions, fusing features from all steps. Extensive experiments on the benchmark dataset illustrate the effectiveness of our framework.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Trans. Pattern Anal. Mach. Intell. 40(4), 834–848 (2017)
Dai, Y., Gieseke, F., Oehmcke, S., Wu, Y., Barnard, K.: Attentional feature fusion. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 3560–3569 (2021)
De Boer, P.T., Kroese, D.P., Mannor, S., Rubinstein, R.Y.: A tutorial on the cross- entropy method. Ann. Oper. Res. 134(1), 19–67 (2005)
Fan, D.P., et al.: Pranet: parallel reverse attention network for polyp segmentation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 263–273. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-59725-2_26
Feng, M., Lu, H., Ding, E.: Attentive feedback network for boundary-aware salient object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1623–1632 (2019)
He, H., et al.: Enhanced boundary learning for glass-like object segmentation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 15859–15868 (2021)
Hu, X., Zhu, L., Fu, C.W., Qin, J., Heng, P.A.: Direction-aware spatial context features for shadow detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7454–7462 (2018)
Huang, S., Lu, Z., Cheng, R., He, C.: Fapn: feature-aligned pyramid network for dense image prediction. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 864–873 (2021)
Huang, Z., Wang, X., Huang, L., Huang, C., Wei, Y., Liu, W.: Ccnet: criss-cross attention for semantic segmentation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision. pp. 603–612 (2019)
Huo, D., Wang, J., Qian, Y., Yang, Y.H.: Glass segmentation with rgb-thermal image pairs. arXiv preprint arXiv:2204.05453 (2022)
Lin, J., He, Z., Lau, R.W.: Rich context aggregation with reflection prior for glass surface detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 13415–13424 (2021)
Margolin, R., Zelnik-Manor, L., Tal, A.: How to evaluate foreground maps? In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255 (2014)
Mattyus, G., Luo, W., Urtasun, R.: Deeproadmapper: extracting road topology from aerial images. In: International Conference on Computer Vision (2017)
Mei, H., et al.: Glass segmentation using intensity and spectral polarization cues. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12622–12631 (2022)
Mei, H., et al.: Don’t hit me! glass detection in real-world scenes. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 3687–3696 (2020)
Mei, H., Yang, X., Yu, L., Zhang, Q., Wei, X., Lau, R.W.: Large-field contextual feature learning for glass detection. IEEE Trans. Pattern Anal. Mach. Intell. 45, 3329–3346 (2022)
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), pp. 565–571. IEEE (2016)
Nguyen, V., Yago Vicente, T.F., Zhao, M., Hoai, M., Samaras, D.: Shadow detection with conditional generative adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4510–4518 (2017)
Qin, X., Zhang, Z., Huang, C., Gao, C., Dehghan, M., Jagersand, M.: Basnet: boundary-aware salient object detection. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 7479–7489 (2019)
Wei, J., Wang, S., Huang, Q.: F3net: fusion, feedback and focus for salient object detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 12321–12328 (2020)
Wei, J., Wang, S., Wu, Z., Su, C., Huang, Q., Tian, Q.: Label decoupling frame- work for salient object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 13025–13034 (2020)
Whelan, T., et al.: Reconstructing scenes with mirror and glass surfaces. ACM Trans. Graph. 37(4), 102–111 (2018)
Xie, E., Wang, W., Wang, W., Ding, M., Shen, C., Luo, P.: Segmenting transparent objects in the wild. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.M. (eds.) Computer Vision – ECCV 2020. ECCV 2020. Lecture Notes in Computer Science, vol. 12358, pp 696–711. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58601-0_41
Xie, E., et al.: Segmenting transparent object in the wild with transformer. arXiv preprint arXiv:2101.08461 (2021)
Yang, X., Mei, H., Xu, K., Wei, X., Yin, B., Lau, R.W.: Where is my mirror? In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 8809–8818 (2019)
Yu, L., et al.: Progressive glass segmentation. IEEE Trans. Image Process. 31, 2920–2933 (2022)
Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2881–2890 (2017)
Zhao, J.X., Liu, J.J., Fan, D.P., Cao, Y., Yang, J., Cheng, M.M.: Egnet: edge guidance network for salient object detection. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 8779–8788 (2019)
Zheng, C., et al.: Glassnet: Label decoupling-based three-stream neural network for robust image glass detection. In: Computer Graphics Forum, vol. 41, pp. 377–388. Wiley Online Library (2022)
Zhou, H., Xie, X., Lai, J.H., Chen, Z., Yang, L.: Interactive two-stream decoder for accurate and fast saliency detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9141–9150 (2020)
Acknowledgment
This work is supported by the National Natural Science Foundation of China under Grant No. 62076058.
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 Singapore Pte Ltd.
About this paper
Cite this paper
Zhang, J., Yang, G., Liu, C. (2023). DCNet: Glass-Like Object Detection via Detail-Guided and Cross-Level Fusion. In: Huang, DS., Premaratne, P., Jin, B., Qu, B., Jo, KH., Hussain, A. (eds) Advanced Intelligent Computing Technology and Applications. ICIC 2023. Lecture Notes in Computer Science, vol 14087. Springer, Singapore. https://doi.org/10.1007/978-981-99-4742-3_38
Download citation
DOI: https://doi.org/10.1007/978-981-99-4742-3_38
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-4741-6
Online ISBN: 978-981-99-4742-3
eBook Packages: Computer ScienceComputer Science (R0)