Name
Abstract | ||
|---|---|---|
Recently, shadow detectors based on Deep Convolutional Neural Networks (DCNN) have lifted the detection performances to a new height. However, the correct detection of mild and very dark shadows remains to be a difficult task. In this work, we propose a new model called Double-stream Atrous Network (DSAN) for shadow detection. It has a double-streams framework: the pooling stream extracts high-level features and the residual stream incorporates low-level features with high-level feature maps from the pooling stream in each single step. We also design new modules such as Atrous Convolution Module (ACM), Multi-layer Atrous Pooling Module (MLAPM), and Cross-stream Residual Module (CSRM) to extract shadow features effectively. On two shadow datasets, our DSAN outperforms several popular shadow detectors based on DCNN. |
Year | DOI | Venue |
|---|---|---|
2020 | 10.1016/j.neucom.2020.07.038 | Neurocomputing |
Keywords | DocType | Volume |
Shadow detection,Deep Convolutional Neural Networks,Atrous Convolution,Double-stream Atrous Network | Journal | 417 |
ISSN | Citations | PageRank |
0925-2312 | 2 | 0.39 |
References | Authors | |
0 | 6 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Dawei Li | 1 | 6 | 0.81 |
| Sifan Wang | 2 | 2 | 0.39 |
| Xue-song Tang | 3 | 9 | 2.86 |
| Weijian Kong | 4 | 5 | 1.77 |
| Guoliang Shi | 5 | 4 | 2.52 |
| Chen Yang | 6 | 172 | 43.55 |