Abstract
Salient object detection in an image attributes to finding an object which stands out from its neighbors. State of the art approaches in salient object detection have used learning-based methods for predicting saliency maps. Typically the features from the images are extracted using CNN architectures as they have become influential in computer vision tasks. In this paper, a bottom-up approach for salient object detection in images is described. Densely Connected Neural Network (DenseNet), a recent CNN architecture which has shown significant improvement in classification tasks, has been used for extracting features from the image. DenseNet has strengthened feature propagation, reduced training parameters and also has a lower error rate compared to other CNN architectures. Features from DenseNet have been used to predict the saliency maps of the images. The experimental results show significant improvements from previous works on saliency.
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
Redmon, J., Divvala, S.K., Girshick, R.B.: You only look once: Unified, real-time object detection. CoRR, abs/1506.02640 (2015)
Ren, S., He, K., Girshick, R.B.: Faster R-CNN: towards real-time object detection with region proposal networks. CoRR, abs/1506.01497 (2015)
Simonyan, K. and Zisserman, A.: Very Deep Convolutional Networks for Large-Scale Image Recognition, arXiv preprint arXiv:1409.1556 (2015)
Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation, in IEEE Conf. Comput.Vis. Pattern Recog., pp. 3431–3440 (2015)
Parkhurst, D., Law, K., and Niebur, E.: Modeling the role of salience in the allocation of overt visual attention, Vision Research, vol. 42, no. 1, pp. 107–123 (2002)
Itti, L. and Koch, C.: Computational modeling of visual attention, Nature reviews neuroscience, vol. 2, no. 3, pp. 194–203 (2001)
He, K., Zhang, X., Ren, S.: Deep residual learning for image recognition. In CVPR, 1, 2, 3, 4, 5, 6 (2016)
Huang, G., Liu, Z.: Weinberger.Densely connected convolutional networks. CoRR, abs/1608.06993 (2016)
Hou, Q., Cheng, M.: Deeply Supervised Salient Object Detection with Short Connections, IEEE Transactions on pattern analysis and machine intelligence, https://doi.org/10.1109/TPAMI.2018.2815688 (2017).
LeCun, Y., Boser, B., Denker, J.S.: Backpropagation applied to handwritten zip code recognition. Neural Computation, 1(4): 541–551 (1989)
Krizhevsky, A., Sutskever, I., and Hinton, G.E.:ImageNet Classification with Deep Convolutional Neural Networks, in Advances in Neural Information Processing Systems (2012)
Srivastava, R.K., Greff, K. and Schmidhuber, J.: Training very deep networks. In NIPS, 1, 2, 5 (2015)
Hochreiter, S. and Schmidhuber, J.: Long Short-Term Memory, Neural Computation, vol. 9, no. 8, pp. 1735–1780 (1997)
Szegedy, C., Liu, W.: Going Deeper with Convolutions, in IEEE International Conference on Computer Vision and Pattern Recognition, Boston, MA, pp. 1-9. https://doi.org/10.1109/CVPR.2015.7298594 (2015)
Han, J., Zhang, D., Wen, S.: Two-Stage Learning to Predict Human Eye Fixations via SDAEs, in IEEE Transactions on Cybernetics, vol. 46, no. 2, pp. 487-498 (Feb 2016)
Jegou, S., Drozdzal, M.: The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation, IEEE (CVPRW), Honolulu, HI, pp. 1175-1183 (2017)
Liu, N. and Han, J.: A Deep Spatial Contextual Long-term Recurrent Convolutional Network for Saliency Detection, IEEE Transactions on Image Processing, vol. 27, no. 7, pp. 3264-3274 (July 2018)
Cornia, M., Baraldi, L.: Predicting Human Eye Fixations via an LSTM-based Saliency Attentive Model, IEEE Transactions on Image Processing, vol. 27, no. 10, pp. 5142-5154 (Oct. 2018)
Quan, H., Feng, S.: Two Birds With One Stone: A Unified Approach to Saliency and Co-Saliency Detection via Multi-Instance Learning, in IEEE Access, vol. 5, pp. 23519-23531 (2017)
Quan, R., Han, J., Zhang, D.: Unsupervised Salient Object Detection via Inferring From Imperfect Saliency Models, in IEEE Transactions on Multimedia, vol. 20, no. 5, pp. 1101-11120 (May 2018)
Wang, J. and Jiang, H. and Yuan, Z.: Salient Object Detection: A Discriminative Regional Feature Integration Approach, International Journal of Computer Vision, vol 123, ISSN 1573-1405 (2017)
Li, G. and Yu, Y.: Deep contrast learning for salient object detection, in IEEE Conf. Comput. Vis. Pattern Recog. (2016)
Gayoung, L., Yu-Wing, T., and Junmo, K.: Deep saliency with encoded low-level distance map and high-level features, in IEEE Conf. Comput. Vis. Pattern Recog., (2016), https://github.com/gylee1103/SaliencyELD.
Wang, L., Wang, L., Lu, H., Zhang, P. and Ruan, X.: Saliency detection with recurrent fully convolutional networks, in Eur. Conf. Comput. Vis. (2016)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Sujatha, P.K., Nivethan, N., Vignesh, R., Akila, G. (2020). Salient Object Detection Using DenseNet Features. In: Smys, S., Iliyasu, A.M., Bestak, R., Shi, F. (eds) New Trends in Computational Vision and Bio-inspired Computing. Springer, Cham. https://doi.org/10.1007/978-3-030-41862-5_168
Download citation
DOI: https://doi.org/10.1007/978-3-030-41862-5_168
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-41861-8
Online ISBN: 978-3-030-41862-5
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)