Feifei Shi, Songlong Zhang, Li Peng. Salient Object Detection Based on Deep Residual Networks and Edge Supervised Learning[J]. Laser & Optoelectronics Progress, 2019, 56(15): 151502
- Laser & Optoelectronics Progress
- Vol. 56, Issue 15, 151502 (2019)
Fig. 1. Network structure
Fig. 2. Edge residuals block structure diagram
Fig. 3. Multi-scale atrous convolution unit
Fig. 4. Contrast of ground truth image. (a) Original ground truth image; (b) modified manual marking diagram
Fig. 5. Contrast of three-category model proposed in our paper and the traditional two-category model. (a) Original image; (b) result of traditional two-classification model; (c) results of proposed three-classification model; (d) ground truth image
Fig. 6. Comparison of saliency maps. (a) Original image; (b) BL; (c) BSCA; (d) RFCN;(e) MDF; (f) DCL; (g) DHS; (h) UCF; (i) proposed method; (j) ground truth image
Fig. 7. Precision-recall curves of the proposed algorithm and other state-of-the-art methods. (a) Results on ECSSD dataset; (b) results on SED2 dataset
|
Table 1. Performance comparison of proposed modules
|
Table 2. Performance comparison of each algorithm
Set citation alerts for the article
Please enter your email address
© Copyright 2018-2021 | Chinese Laser Press. All Rights Reserved 沪ICP备15018463号-20