Abstract
Weakly supervised salient object detection aims to address the limitations of fully supervised methods that heavily rely on pixel-level data. However, the sparse nature of weak labels often results in suboptimal detection accuracy. Drawing inspiration from human visual attention mechanisms, we propose a Mixed-Supervised Learning method to mitigate this issue. Mixed-Supervised Learning refers to training a neural network with hybrid data. Specifically, we propose a two-stage training strategy. In stage I, the model is supervised by a large number of scribble annotations so that it can roughly locate salient objects. In stage II, a small number of pixel-level labels are used for learning to endow the model with detail decoding capability. Our training strategy decomposes the SOD task into two sub-tasks, object localization and detail refinement, and we design a corresponding network, LRNet, which includes the supplementary detail information, a Feature Attention module (FA), and a Detail Refinement module (DF). The two-stage training strategy is simple and generalizable. Extensive experiments demonstrate the effectiveness of the training strategy, and our model detection accuracy surpasses the existing state-of-the-art models of weakly supervised learning, even reaching fully supervised results. Besides, experiments on COD and RSI SOD tasks demonstrate the generality of our method. Our code will be released at https://github.com/nightmengna/LRNet.
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
Yun, Y.K., Lin, W.: Selfreformer: Self-refined network with transformer for salient object detection. arXiv preprint arXiv:2205.11283 (2022)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. pp. 770–778 (2016)
Wang, W., et al.: Pvt v2: Improved baselines with pyramid vision transformer. Computational Visual Media 8(3), 415–424 (2022)
Liu, N., Zhang, N., Wan, K., Shao, L., Han, J.: Visual saliency transformer. In: Proceedings of the IEEE/CVF international conference on computer vision, pp. 4722–4732 (2021)
Wu, Z., Su, L., Huang, Q.: Decomposition and completion network for salient object detection. IEEE Trans. Image Process. 30, 6226–6239 (2021)
Piao, Y., Wang, J., Zhang, M., Lu, H.: Mfnet: Multi-filter directive network for weakly supervised salient object detection, pp. 4136–4145 (2021)
Liu, Y., Wang, P., Cao, Y., Liang, Z., Lau, R.W.H.: Weakly- supervised salient object detection with saliency bounding boxes. IEEE Transac- tions on Image Processing 30, 4423–4435 (2021)
Zhang, J., Yu, X., Li, A., Song, P., Liu, B., Dai, Y.: Weakly- supervised salient object detection via scribble annotations, pp. 12546–12555 (2020)
Gao, S., et al.: Weakly-supervised salient object detection using point supervison. National conference on artificial intelligence (2022)
Yu, S., Zhang, B., Xiao, J., Lim, E.G.: Structure-consistent weakly supervised salient object detection with local saliency coherence 35(4), 3234–3242 (2021)
Wang, X., Al-Huda, Z., Peng, B.: Weakly-supervised salient object detection through object segmentation guided by scribble annotations. In: 2021 16th International Conference on Intelligent Systems and Knowledge Engineering (ISKE), pp. 304–312. IEEE (2021)
Gao, F., et al.: Segmentation only uses sparse annotations: Unified weakly and semi-supervised learning in medical images. Med. Image Anal. 80, 102515 (2022)
Cong, R., et al.: A weakly supervised learning framework for salient object detection via hybrid labels. IEEE (2022)
Ronneberger, O., Fischer, P., Brox, T.: U-net: Convolutional networks for biomedical image segmentation. In: International Conference on Medical image computing and computer-assisted intervention, pp. 234–241. Springer (2015)
Pang, Y., Zhao, X., Xiang, T.-Z., Zhang, L., Lu, H.: Zoom in and out: A mixed-scale triplet network for camouflaged object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2160–2170 (2022)
Zhou, B., Yang, G., Wan, X., Wang, Y., Liu, C., Wang, H.: A simple network with progressive structure for salient object detection, pp. 397–408 (2021)
Zhao, K., Gao, S., Wang, W., Cheng, M.-M.: Optimizing the f-measure for threshold-free salient object detection, pp. 8849–8857 (2019)
Wang, L., et al.: Learning to detect salient objects with image-level supervision, pp. 136–145 (2017)
Yang, C., Zhang, L., Lu, H., Ruan, X., Yang, M.-H.: Saliency detection via graph-based manifold ranking, pp. 3166–3173 (2013)
Yan, Q., Xu, L., Shi, J., Jia, J.: Hierarchical saliency detection, pp. 1155–1162 (2013)
Li, Y., Hou, X., Koch, C., Rehg, J.M., Yuille, A.L.: The secrets of salient object segmentation, pp. 280–287 (2014)
Li, G., Yu, Y.: Visual saliency based on multiscale deep features, pp. 5455–5463 (2015)
Ran, M., Lihi, Z.-M., Tal, A.: How to evaluate foreground maps? In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 248–255 (2014)
Perazzi, F., Philipp, K., Pritch, Y., Hornung, A.: Saliency filters: contrast based filtering for salient region detection. In: 2012 IEEE conference on computer vision and pattern recognition, pp. 733–740. IEEE (2012)
Fan, D.-P., Cheng, M.-M., Liu, Y., Li, T., Borji, A.: Structure- measure: A new way to evaluate foreground maps. In: Proceedings of the IEEE international conference on computer vision, pp. 4548–4557 (2017)
Zhao, X., Pang, Y., Zhang, L., Lu, H., Zhang, L.: Suppress and balance: a simple gated network for salient object detection. In: European conference on computer vision, pp. 35–51. Springer (2020)
Pang, Y., Zhao, X., Zhang, L., Lu, H.: Multi-scale interactive network for salient object detection. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 9413–9422 (2020)
Qin, X., Zhang, Z., Huang, C., Dehghan, M., Zaiane, O.R., Jagersand, M.: U2-net: Going deeper with nested u-structure for salient object detection. Pattern recognition 106, 107404 (2020)
Piao, Y., Wu, W, Zhang, M., Jiang, Y., Lu, H.: Noise- sensitive adversarial learning for weakly supervised salient object detection. IEEE Transactions on Multimedia (2022)
Fan, D.-P., Ji, G.-P., Sun, G., Cheng, M.-M., Shen, J., Shao, L.: Camouflaged object detection. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 2777–2787 (2020)
Le, T.-N., Nguyen, T.V., Nie, Z., Tran, M., Sugimoto, A.: Anabranch network for camouflaged object segmentation. Computer Vision and Image Understanding 184, 45–56 (2019)
Wu, W., Qi, H., Rong, Z., Liu, L., Su, H.: Scribble- supervised segmentation of aerial building footprints using adversarial learning. IEEE Access 6, 58898–58911 (2018)
Huang, Z., Xiang, T.-Z., Chen, H.-X., Dai, H.: Scribble-based boundary-aware network for weakly supervised salient object detection in remote sensing images. ISPRS J. Photogramm. Remote. Sens. 191, 290–301 (2022)
He, R., Dong, Q., Lin, J., Lau, R.W.H.: Weakly-supervised camouflaged object detection with scribble annotations. arXiv preprint arXiv:2207.14083 (2022)
Acknowledgment
This work is supported by the National Natural Science Foundation of China [grant number 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
Gong, C., Yang, G., Dong, H. (2023). A Simple Mixed-Supervised Learning Method for Salient Object Detection. 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 14090. Springer, Singapore. https://doi.org/10.1007/978-981-99-4761-4_6
Download citation
DOI: https://doi.org/10.1007/978-981-99-4761-4_6
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-4760-7
Online ISBN: 978-981-99-4761-4
eBook Packages: Computer ScienceComputer Science (R0)