Skip to main content
SpringerLink
Log in

Multi-scale Residual Interaction for RGB-D Salient Object Detection

  • Conference paper
  • First Online:
Computer Vision – ACCV 2022 (ACCV 2022)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13843))

Included in the following conference series:

Abstract

RGB-D salient object detection (SOD) is used to detect the most attractive object in the scene. There is a problem in front of the existing RGB-D SOD task: how to integrate the different context information between the RGB and depth map effectively. In this work, we propose the Siamese Residual Interactive Refinement Network (SiamRIR) equipped with the encoder and decoder to handle the above problem. Concretely, we adopt the Siamese Network shared parameters to encode two modalities and fuse them during decoding phase. Then, we design the Multi-scale Residual Interactive Refinement Block (RIRB) which contains Residual Interactive Module (RIM) and Residual Refinement Module (RRM). This block utilizes the multi-type cues to fuse and refine features, where RIM takes interaction between modalities to integrate the complementary regions with residual manner, and RRM refines features during fusion phase by incorporating spatial detail context with multi-scale manner. Extensive experiments on five benchmarks demonstrate that our method outperforms the state-of-the-art RGB-D SOD methods both quantitatively and qualitatively.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 84.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 109.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Wang, W., Lai, Q., Fu, H., Shen, J., Ling, H., Yang, R.: Salient object detection in the deep learning era: an in-depth survey. IEEE Trans. Pattern Anal. Mach. Intell. 44(6), 3239–3259 (2021)

    Article  Google Scholar 

  2. Cheng, M.M., Mitra, N.J., Huang, X., Torr, P.H., Hu, S.M.: Global contrast based salient region detection. IEEE Trans. Pattern Anal. Mach. Intell. 37(3), 569–582 (2014)

    Article  Google Scholar 

  3. Borji, A., Cheng, M.-M., Hou, Q., Jiang, H., Li, J.: Salient object detection: a survey. Comput. Vis. Media 5(2), 117–150 (2019). https://doi.org/10.1007/s41095-019-0149-9

    Article  Google Scholar 

  4. Wang, P., et al.: Understanding convolution for semantic segmentation, pp. 1451–1460 (2018)

    Google Scholar 

  5. Noh, H., Hong, S., Han, B.: Learning deconvolution network for semantic segmentation, pp. 1520–1528 (2015)

    Google Scholar 

  6. Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation, pp. 3431–3440 (2015)

    Google Scholar 

  7. Chen, Z.M., Jin, X., Zhao, B.R., Zhang, X., Guo, Y.: HCE: hierarchical context embedding for region-based object detection. IEEE Trans. Image Process. 30, 6917–6929 (2021)

    Article  Google Scholar 

  8. Hu, H., Gu, J., Zhang, Z., Dai, J., Wei, Y.: Relation networks for object detection, pp. 3588–3597 (2018)

    Google Scholar 

  9. Liu, W.: Pair-based uncertainty and diversity promoting early active learning for person re-identification. ACM Trans. Intell. Syst. Technol. (TIST) 11(2), 1–15 (2020)

    Article  Google Scholar 

  10. Zheng, Z., Zheng, L., Yang, Y.: A discriminatively learned CNN embedding for person reidentification. ACM Trans. Multimed. Comput. Commun. Appl. 14(1), 1–20 (2017)

    Article  Google Scholar 

  11. Mahadevan, V., Vasconcelos, N.: Biologically inspired object tracking using center-surround saliency mechanisms. IEEE Trans. Pattern Anal. Mach. Intell. 35(3), 541–554 (2012)

    Article  Google Scholar 

  12. Yilmaz, A., Javed, O., Shah, M.: Object tracking: a survey. ACM Comput. Surv. 38(4), 13-es (2006)

    Google Scholar 

  13. Wang, W., Zhao, S., Shen, J., Hoi, S.C., Borji, A.: Salient object detection with pyramid attention and salient edges, pp. 1448–1457 (2019)

    Google Scholar 

  14. Hou, Q., Cheng, M.M., Hu, X., Borji, A., Tu, Z., Torr, P.H.: Deeply supervised salient object detection with short connections, pp. 3203–3212 (2017)

    Google Scholar 

  15. Chen, S., Tan, X., Wang, B., Hu, X.: Reverse attention for salient object detection, pp. 234–250 (2018)

    Google Scholar 

  16. Zhang, X., Wang, T., Qi, J., Lu, H., Wang, G.: Progressive attention guided recurrent network for salient object detection, pp. 714–722 (2018)

    Google Scholar 

  17. Jiang, H., Wang, J., Yuan, Z., Wu, Y., Zheng, N., Li, S.: Salient object detection: a discriminative regional feature integration approach, pp. 2083–2090 (2013)

    Google Scholar 

  18. Zhao, J.X., Liu, J.J., Fan, D.P., Cao, Y., Yang, J., Cheng, M.M.: EGNet: edge guidance network for salient object detection, pp. 8779–8788 (2019)

    Google Scholar 

  19. Cheng, Y., Fu, H., Wei, X., Xiao, J., Cao, X.: Depth enhanced saliency detection method, pp. 23–27 (2014)

    Google Scholar 

  20. Ren, J., Gong, X., Yu, L., Zhou, W., Ying Yang, M.: Exploiting global priors for RGB-D saliency detection, pp. 25–32 (2015)

    Google Scholar 

  21. Cong, R., Lei, J., Fu, H., Hou, J., Huang, Q., Kwong, S.: Going from RGB to RGBD saliency: a depth-guided transformation model. IEEE Trans. Cybern. 50(8), 3627–3639 (2019)

    Article  Google Scholar 

  22. Song, H., Liu, Z., Du, H., Sun, G., Le Meur, O., Ren, T.: Depth-aware salient object detection and segmentation via multiscale discriminative saliency fusion and bootstrap learning. IEEE Trans. Image Process. 26(9), 4204–4216 (2017)

    Article  MathSciNet  MATH  Google Scholar 

  23. Zhao, J.X., Cao, Y., Fan, D.P., Cheng, M.M., Li, X.Y., Zhang, L.: Contrast prior and fluid pyramid integration for RGBD salient object detection, pp. 3927–3936 (2019)

    Google Scholar 

  24. Chen, H., Li, Y.: Three-stream attention-aware network for RGB-D salient object detection. IEEE Trans. Image Process. 28(6), 2825–2835 (2019)

    Article  MathSciNet  MATH  Google Scholar 

  25. Ciptadi, A., Hermans, T., Rehg, J.M.: An in depth view of saliency (2013)

    Google Scholar 

  26. Zhao, S., Chen, M., Wang, P., Cao, Y., Zhang, P., Yang, X.: RGB-D salient object detection via deep fusion of semantics and details. Comput. Animation Virtual Worlds 31(4–5), e1954 (2020)

    Google Scholar 

  27. Chen, H., Li, Y., Su, D.: Multi-modal fusion network with multi-scale multi-path and cross-modal interactions for RGB-D salient object detection. Pattern Recogn. 86, 376–385 (2019)

    Article  Google Scholar 

  28. Qu, L., He, S., Zhang, J., Tian, J., Tang, Y., Yang, Q.: RGBD salient object detection via deep fusion. IEEE Trans. Image Process. 26(5), 2274–2285 (2017)

    Article  MathSciNet  MATH  Google Scholar 

  29. Fan, D.P., Lin, Z., Zhang, Z., Zhu, M., Cheng, M.M.: Rethinking RGB-D salient object detection: models, data sets, and large-scale benchmarks. IEEE Trans. Neural Netw. Learn. Syst. 32(5), 2075–2089 (2020)

    Article  Google Scholar 

  30. Chen, H., Deng, Y., Li, Y., Hung, T.Y., Lin, G.: RGBD salient object detection via disentangled cross-modal fusion. IEEE Trans. Image Process. 29, 8407–8416 (2020)

    Article  MATH  Google Scholar 

  31. Peng, H., Li, B., Xiong, W., Hu, W., Ji, R.: RGBD salient object detection: a benchmark and algorithms, pp. 92–109 (2014)

    Google Scholar 

  32. Liu, Z., Shi, S., Duan, Q., Zhang, W., Zhao, P.: Salient object detection for RGB-D image by single stream recurrent convolution neural network. Neurocomputing 363, 46–57 (2019)

    Article  Google Scholar 

  33. Liu, D., Hu, Y., Zhang, K., Chen, Z.: Two-stream refinement network for RGB-D saliency detection, pp. 3925–3929 (2019)

    Google Scholar 

  34. Zhang, Z., Lin, Z., Xu, J., Jin, W.D., Lu, S.P., Fan, D.P.: Bilateral attention network for RGB-D salient object detection. IEEE Trans. Image Process. 30, 1949–1961 (2021)

    Article  Google Scholar 

  35. Huang, N., Luo, Y., Zhang, Q., Han, J.: Discriminative unimodal feature selection and fusion for RGB-D salient object detection. Pattern Recogn. 122, 108359 (2022)

    Article  Google Scholar 

  36. Chen, Q., et al.: EF-Net: a novel enhancement and fusion network for RGB-D saliency detection. Pattern Recogn. 112, 107740 (2021)

    Article  Google Scholar 

  37. Wang, J., Chen, S., Lv, X., Xu, X., Hu, X.: Guided residual network for RGB-D salient object detection with efficient depth feature learning. Vis. Comput. 38(5), 1803–1814 (2022)

    Article  Google Scholar 

  38. Bromley, J., et al.: Signature verification using a “siamese’’ time delay neural network. Int. J. Pattern Recogn. Artif. Intell. 7(04), 669–688 (1993)

    Article  Google Scholar 

  39. Chan, S., Tao, J., Zhou, X., Bai, C., Zhang, X.: Siamese implicit region proposal network with compound attention for visual tracking. IEEE Trans. Image Process. 31, 1882–1894 (2022)

    Article  Google Scholar 

  40. Fan, H., Ling, H.: Siamese cascaded region proposal networks for real-time visual tracking, pp. 7952–7961 (2019)

    Google Scholar 

  41. Zhao, X., Zhang, L., Pang, Y., Lu, H., Zhang, L.: A single stream network for robust and real-time RGB-D salient object detection, pp. 646–662 (2020)

    Google Scholar 

  42. Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database, pp. 248–255 (2009)

    Google Scholar 

  43. Fu, K., Fan, D.P., Ji, G.P., Zhao, Q.: JL-DCF: joint learning and densely-cooperative fusion framework for RGB-D salient object detection, pp. 3052–3062 (2020)

    Google Scholar 

  44. Zhang, P., Liu, W., Zeng, Y., Lei, Y., Lu, H.: Looking for the detail and context devils: high-resolution salient object detection. IEEE Trans. Image Process. 30, 3204–3216 (2021)

    Article  Google Scholar 

  45. Ju, R., Ge, L., Geng, W., Ren, T., Wu, G.: Depth saliency based on anisotropic center-surround difference, pp. 1115–1119 (2014)

    Google Scholar 

  46. Niu, Y., Geng, Y., Li, X., Liu, F.: Leveraging stereopsis for saliency analysis, pp. 454–461 (2012)

    Google Scholar 

  47. Liu, C., Yuen, J., Torralba, A.: Sift flow: dense correspondence across scenes and its applications. IEEE Trans. Pattern Anal. Mach. Intell. 33(5), 978–994 (2010)

    Article  Google Scholar 

  48. Chen, H., Li, Y.: Progressively complementarity-aware fusion network for RGB-D salient object detection, pp. 3051–3060 (2018)

    Google Scholar 

  49. Piao, Y., Ji, W., Li, J., Zhang, M., Lu, H.: Depth-induced multi-scale recurrent attention network for saliency detection, pp. 7254–7263 (2019)

    Google Scholar 

  50. Huang, Z., Chen, H.X., Zhou, T., Yang, Y.Z., Liu, B.Y.: Multi-level cross-modal interaction network for RGB-D salient object detection. Neurocomputing 452, 200–211 (2021)

    Article  Google Scholar 

  51. Li, C., et al.: Asif-net: attention steered interweave fusion network for RGB-D salient object detection. IEEE Trans. Cybern. 51(1), 88–100 (2020)

    Article  MathSciNet  Google Scholar 

  52. Zhou, X., Wen, H., Shi, R., Yin, H., Zhang, J., Yan, C.: FANet: feature aggregation network for RGBD saliency detection. Signal Process.: Image Commun. 102, 116591 (2022)

    Google Scholar 

  53. Jin, X., Guo, C., He, Z., Xu, J., Wang, Y., Su, Y.: FCMNet: frequency-aware cross-modality attention networks for RGB-D salient object detection. Neurocomputing 491, 414–425 (2022)

    Article  Google Scholar 

Download references

Acknowledgements

This work was supported in part by the National Natural Science Foundation of China [grant nos. 61922064, U2033210, 62101387] and Zhejiang Xinmiao Talents Program [grant nos. 2022R429B046].

Author information

Authors and Affiliations

  1. College of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou, China

    Mingjun Hu, Xiaoqin Zhang & Li Zhao

Authors
  1. Mingjun Hu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Xiaoqin Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Li Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Xiaoqin Zhang .

Editor information

Editors and Affiliations

  1. University of Wollongong, Wollongong, NSW, Australia

    Lei Wang

  2. University of Bonn, Bonn, Germany

    Juergen Gall

  3. University of Adelaide, Adelaide, SA, Australia

    Tat-Jun Chin

  4. National Institute of Informatics, Tokyo, Japan

    Imari Sato

  5. Johns Hopkins University, Baltimore, MD, USA

    Rama Chellappa

Rights and permissions

Reprints and permissions

Copyright information

© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Hu, M., Zhang, X., Zhao, L. (2023). Multi-scale Residual Interaction for RGB-D Salient Object Detection. In: Wang, L., Gall, J., Chin, TJ., Sato, I., Chellappa, R. (eds) Computer Vision – ACCV 2022. ACCV 2022. Lecture Notes in Computer Science, vol 13843. Springer, Cham. https://doi.org/10.1007/978-3-031-26313-2_35

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-26313-2_35

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-26312-5

  • Online ISBN: 978-3-031-26313-2

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation