Abstract
Deep convolutional neural networks (CNNs) have recently achieved great improvements in salient object detection. Most existing CNN-based models adopt cross entropy loss to optimize the networks for its capability in probability prediction. The function of cross entropy loss in salient object detection can be seemed as a pixel-wise label classification for images, which automatically predict whether the pixel is salient or non-salient. However, cross entropy loss pays attention to each single pixel of image when classifying the label, which doesn’t consider the relationship with other pixels. In this paper, we propose an additional loss function, called group loss, to improve the above limitation of cross entropy loss. In our model, group loss as well as cross entropy loss work together to optimize the network for better saliency detection performance. The purpose of group loss is to make the difference between salient pixels smaller while the distance between salient and non-salient pixels as large as possible. Meanwhile, due to the large computation cost of pixel-wise comparisons, we design a superpixel pooling layer for computing group loss with no additional parameters, which converts the computation of group loss to superpixel level. The experimental results show that the introduction of group loss improves the performance of CNN network in salient object detection, which makes the boundaries of salient objects more distinct.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Zhu, W., Liang, S., Wei, Y., Sun, J.: Saliency optimization from robust background detection. In: 27th IEEE Conference on Computer Vision and Pattern Recognition, Columbus, pp. 2814–2821. IEEE Press (2014)
Yang, C., Zhang, L., Lu, H., Ruan, X., Yang, M.H.: Saliency detection via graph-based manifold ranking. In: 26th IEEE Conference on Computer Vision and Pattern Recognition, Portland, pp. 3166–3173. IEEE Press (2013)
Jiang, B., Zhang, L., Lu, H., Yang, C., Yang, M.H.: Saliency detection via absorbing Markov chain. In: 14th IEEE International Conference on Computer Vision, Sydney, pp. 1665–1672. IEEE Press (2013)
Cheng, M.M., Warrell, J., Lin, W.Y., Zheng, S., Vineet, V., Crook, N.: Efficient salient region detection with soft image abstraction. In: 14th IEEE International Conference on Computer Vision, Sydney, pp. 1529–1536. IEEE Press (2013)
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)
Achanta, R., Hemami, S., Estrada, F., Susstrunk, S.: Frequency-tuned salient region detection. In: 22nd IEEE Conference on Computer Vision and Pattern Recognition, Miami, pp. 1597–1604. IEEE Press (2009)
Lecun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Zhao, R., Ouyang, W., Li, H., Wang, X.: Saliency detection by multi-context deep learning. In: The IEEE Conference on Computer Vision and Pattern Recognition on Proceedings, Boston, pp. 1265–1274. IEEE Press (2015)
Li, G., Yu, Y.: Visual saliency based on multiscale deep features. In: The IEEE Conference on Computer Vision and Pattern Recognition on Proceedings, Boston, pp. 5455–5463. IEEE Press (2015)
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)
Liu, T., et al.: Learning to detect a salient object. IEEE Trans. Pattern Anal. Mach. Intell. 33(2), 353–367 (2011)
Yan, Q., Xu, L., Shi, J., Jia, J.: Hierarchical saliency detection. In: The IEEE Conference on Computer Vision and Pattern Recognition on Proceedings, Portland, Oregon, pp. 1155–1162. IEEE Press (2013)
Li, Y., Hou, X., Koch, C., Rehg, J., Yuille, A.: The secrets of salient object segmentation. In: The IEEE Conference on Computer Vision and Pattern Recognition on Proceedings, Columbus, pp. 280–287. IEEE Press (2014)
Alpert, S., Galun, M., Basri, R., Brandt, A.: Image segmentation by probabilistic bottom-up aggregation and cue integration. In: The IEEE Conference on Computer Vision and Pattern Recognition on Proceedings, Minneapolis, pp. 1–8. IEEE Press (2007)
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, Portland, pp. 2083–2090. IEEE Press (2013)
Lee, G., Tai, Y.W., Kim, J.: Deep saliency with encoded low level distance map and high level features. In: The IEEE Conference on Computer Vision and Pattern Recognition on Proceedings, Las Vegas, pp. 660–668. IEEE Press (2016)
Chen, T., Lin, L., Liu, L., Luo, X., Li, X.: DISC: deep image saliency computing via progressive representation learning. IEEE Trans. Neural Netw. Learn. Syst. 27(6), 1135–1149 (2016)
Acknowledgments
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
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Hua, Y., Gu, X. (2019). Group Loss: An Efficient Strategy for Salient Object Detection. In: Gedeon, T., Wong, K., Lee, M. (eds) Neural Information Processing. ICONIP 2019. Communications in Computer and Information Science, vol 1142. Springer, Cham. https://doi.org/10.1007/978-3-030-36808-1_12
Download citation
DOI: https://doi.org/10.1007/978-3-030-36808-1_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-36807-4
Online ISBN: 978-3-030-36808-1
eBook Packages: Computer ScienceComputer Science (R0)