Abstract
AbstractBuilding upon fully convolutional networks (FCNs), deep learning-based salient object detection (SOD) methods achieve gratifying performance in many vision tasks, including surface defect detection. However, most existing FCN-based methods still suffer from the coarse object edge predictions. The state-of-the-art methods employ intricate feature aggregation techniques to refine boundaries, but they are often too computational cost to deploy in the real application. This paper proposes a semantics guided detection paradigm for salient object detection. Guided atrous pyramid module is first applied on the top feature to segment complete salient semantics. Query context modules are further used to build relation maps between saliency and structural information from the top-down pathway. These two modules allow the semantic features to flow throughout the decoder phase, yielding detail enriched saliency predictions. Experimental results demonstrate that the proposed method performs favorably against the state-of-the-art methods on surface defect detection and SOD benchmarks. In addition, this method can detect at 27 FPS in a fully convolutional fashion without any post-processing, which has the potential for real-time detection.
Funder
Science Fund for Creative Research Groups
Publisher
Springer Science and Business Media LLC
Subject
Computer Graphics and Computer-Aided Design,Computer Vision and Pattern Recognition,Software
Reference61 articles.
1. Donoser, M., Urschler, M., Hirzer, M., Bischof, H.: Saliency driven total variation segmentation. In 2009 IEEE 12th international conference on computer vision, pp. 817-824 (2009)
2. Borji, A., Frintrop, S., Sihite, D. N., Itti, L.: Adaptive object tracking by learning background context. In 2012 IEEE computer society conference on computer vision and pattern recognition workshops, pp. 23-30 (2012)
3. Hong, S., You, T., Kwak, S., Han, B.: Online tracking by learning discriminative saliency map with convolutional neural network. In International conference on machine learning, pp. 597-606 (2015)
4. Zhao, H., Mao, X., Jin, X., Shen, J., Wei, F., Feng, J.: Real-time saliency-aware video abstraction. Vis. Comput. 25(11), 973–984 (2009)
5. Cheng, M.M., Zhang, F.L., Mitra, N.J., Huang, X., Hu, S.M.: Repfinder: finding approximately repeated scene elements for image editing. ACM Trans. Graph. 29(4), 1–8 (2010)
Cited by
4 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献