Abstract
One of the most challenging issue in visual saliency detection is to discover and integrate meaningful features through deep neural networks. Saliency detection model should be carefully designed to extract sufficient features from different levels and reorganize them into the final prediction. In this paper, we propose an efficient saliency detection framework by introducing multi-scale representation and multi-level combination to deep convolutional neural networks. The main idea of our proposed model is to optimize intra-level feature extraction and inter-level feature combination, so that both saliency semantic and object details can be correctly preserved in final saliency maps. The model utilizes parallel dilated convolutions and pyramid pooling structures to enhance local details and acquire multi-scale feature representation. Feature maps of different resolutions are integrated by performing hierarchical combination in the encoder and decoder parts respectively. As a result, the model can better retain detail information during feature extraction and locate salient regions for saliency map recovery. Experimental results show that our model achieves state-of-the-art performance on several representative datasets.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Gao, Y., Wang, M., Tao, D., Ji, R., Dai, Q.: 3-D Object Retrieval and Recognition With Hypergraph Analysis. IEEE Trans. Image Process. 21(9), 4290–4303 (2012)
Borji, A., Frintrop, S., Sihite, D.N., Itti, L.: Adaptive object tracking by learning background context. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, pp. 23–30, Providence, RI (2012)
Wang, Z., Chen, T., Li, G., Xu, R., Lin, L.: Multi-label image recognition by recurrently discovering attentional regions. In: 16th IEEE International Conference on Computer Vision, pp. 464–472. IEEE Press, Venice (2017)
Zhang, G.X., Cheng, M.M., Hu, S.M., Martin, R.R.: A Shape-preserving Approach to Image Resizing. Comput. Graph. Forum 28(7), 1897–1906 (2009)
Wei, Y., Feng, J., Liang, X., Cheng, M.M., Zhao, Y., Yan, S.: Object region mining with adversarial erasing: a simple classification to semantic segmentation approach. In: 30th IEEE Conference on Computer Vision and Pattern Recognition, pp. 6488–6496. IEEE Press, Honolulu (2017)
Itti, L., Koch, C., Niebur, E.: A Model of Saliency-based Visual Attention for Rapid Scene Analysis. IEEE Trans. Pattern Anal. Mach. Intell. 20(11), 1254–1259 (1998)
Achanta, R., Hemami, S., Estrada, F., Susstrunk, S.: Frequency-tuned salient region detection. In: 22th IEEE Conference on Computer Vision and Pattern Recognition, pp. 1597–1604. IEEE Press, Miami (2009)
Cheng, M.M., Zhang, G.X., Mitra, N.J., Huang, X., Hu, S.M.: Global Contrast Based Salient Region Detection. IEEE Trans. Pattern Anal. Mach. Intell. 37(3), 409–416 (2011)
Li, X., Lu, H., Zhang, L., Xiang, R., Yang, M.H.: Saliency detection via dense and sparse reconstruction. In: 26th IEEE Conference on Computer Vision and Pattern Recognition, pp. 2976–2983. IEEE Press, Portland (2013)
Jiang, H., Wang, J., Yuan, Z., Wu, Y., Zheng, N., Li, S.: Salient object detection: a discriminative regional feature integration approach. In: 26th IEEE Conference on Computer Vision and Pattern Recognition, pp. 2083–2090. IEEE Press, Portland (2013)
He, S., Lau, R.W.H., Liu, W., Huang, Z., Yang, Q.: SuperCNN: a superpixelwise convolutional neural network for salient object detection. Int. J. Comput. Vis. 115(3), 330–344 (2015). https://doi.org/10.1007/s11263-015-0822-0
Zhao, R., Ouyang, W., Li, H., Wang, X.: Saliency detection by multi-context deep learning. In: 28th IEEE Conference on Computer Vision and Pattern Recognition, pp. 1265–1274. IEEE Press, Boston (2015)
Lee, G., Tai, Y.W., Kim, J.: Deep saliency with encoded low level distance map and high level features. In: 29th IEEE Conference on Computer Vision and Pattern Recognition, pp. 660–668. IEEE Press, Las Vegas (2016)
Li, X., Zhao, L., Wei, L., Yang, M.H.: DeepSaliency: multi-task deep neural network model for salient object detection. IEEE Trans. Image Process. 25(8), 3919–3930 (2016)
Luo, Z., Mishra, A., Achkar, A., Eichel, J., Li, S.Z., Jodoin, P.M.: Non-local deep features for salient object detection. In: 30th IEEE Conference on Computer Vision and Pattern Recognition, pp. 6593–6601. IEEE Press, Honolulu (2017)
Zhang, P., Wang, D., Lu, H., Wang, H., Yin, B.: Learning uncertain convolutional features for accurate saliency detection. In: 16th IEEE International Conference on Computer Vision, pp. 212–221. IEEE Press, Venice (2017)
Zhang, P., Wang, D., Lu, H., Wang, H., Ruan, X.: Amulet: aggregating multi-level convolutional features for salient object detection. In: 16th IEEE International Conference on Computer Vision, pp. 202–211. IEEE Press, Venice (2017)
Li, G., Yu, Y.: Contrast-oriented deep neural networks for salient object detection. IEEE Trans. Neural Netw. Learn. Syst. 29(12), 6038–6051 (2018)
Wang, L., Wang, L., Lu, H., Zhang, P., Ruan, X.: Salient object detection with recurrent fully convolutional networks. IEEE Trans. Pattern Anal. Mach. Intell. 41(7), 1734–1746 (2019)
Hou, Q., Cheng, M.M., Hu, X., Borji, A., Tu, Z., Torr, P.H.S.: Deeply supervised salient object detection with short connections. IEEE Trans. Pattern Anal. Mach. Intell. 41(4), 815–828 (2019)
Wang, T., et al.: Detect globally, refine locally: a novel approach to saliency detection. In: 31th IEEE Conference on Computer Vision and Pattern Recognition, pp. 3127–3135. IEEE Press, Salt Lake City (2018)
Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: 28th IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431–3440. IEEE Press, Boston (2015)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 29th IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778. IEEE Press, Las Vegas (2016)
Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: 30th IEEE Conference on Computer Vision and Pattern Recognition, pp. 6230–6239. IEEE Press, Honolulu (2017)
Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28
Krähenbühl, P., Koltun, V.: Efficient inference in fully connected CRFs with gaussian edge potentials. In: Advances in Neural Information Processing Systems (2011)
Wang, L., et al.: Learning to detect salient objects with image-level supervision. In: 29th IEEE Conference on Computer Vision and Pattern Recognition, pp. 3796–3805. IEEE Press, Honolulu (2017)
Yan, Q., Xu, L., Shi, J., Jia, J.: Hierarchical saliency detection. In: 26th IEEE Conference on Computer Vision and Pattern Recognition, pp. 1155–1162. IEEE Press, Portland (2013)
Li, Y., Hou, X., Koch, C., Rehg, J.M., Yuille, A.L.: The secrets of salient object segmentation. In: 27th IEEE Conference on Computer Vision and Pattern Recognition, pp. 280–287. IEEE Press, Columbus (2014)
Liu, T., Sun, J., Zheng, N., Tang, X., Shum, H.: Learning to detect a salient object. In: 20th IEEE Conference on Computer Vision and Pattern Recognition, pp. 353–367. IEEE Press, Minneapolis (2007)
Li, G., Yu, Y.: Visual saliency based on multiscale deep features. In: 27th IEEE Conference on Computer Vision and Pattern Recognition, pp. 5455–5463. IEEE Press, Boston (2015)
Alpert, S., Galun, M., Basri, R., Brandt, A.: Image segmentation by probabilistic bottom-up aggregation and cue integration. IEEE Trans. Pattern Anal. Mach. Intell. 34(2), 315–327 (2012)
Cornia, M., Baraldi, L., Serra, G., Cucchiara, R.: A deep multi-level network for saliency prediction. In: 23th International Conference on Pattern Recognition, pp. 3488–3493. Amsterdam (2016)
Acknowledgements
This work was supported in part by National Natural Science Foundation of China under grant 61771145 and 61371148.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Zhou, L., Gu, X. (2020). Enriched Feature Representation and Combination for Deep Saliency Detection. In: Farkaš, I., Masulli, P., Wermter, S. (eds) Artificial Neural Networks and Machine Learning – ICANN 2020. ICANN 2020. Lecture Notes in Computer Science(), vol 12396. Springer, Cham. https://doi.org/10.1007/978-3-030-61609-0_55
Download citation
DOI: https://doi.org/10.1007/978-3-030-61609-0_55
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-61608-3
Online ISBN: 978-3-030-61609-0
eBook Packages: Computer ScienceComputer Science (R0)