Abstract | ||
---|---|---|
•The “Gate” structure extracts powerful features for object detection.•Two-branch structure predicts the locations and categories ofobjects respectively, where each branch learns different parameters for different tasks.•The inter-class loss help detectors learn the discrepant information between categories and better differentiate similar objects of different categories•The experimental results demonstrate that G-CNN outperforms the state-of-the-art approaches, with a mAP of 40.9% at 10.6 FPS. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1016/j.patcog.2019.107131 | Pattern Recognition |
Keywords | DocType | Volume |
Gated CNN,object detection,multi-scale feature layers,explainable CNN | Journal | 105 |
Issue | ISSN | Citations |
1 | 0031-3203 | 3 |
PageRank | References | Authors |
0.36 | 0 | 7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jin Yuan | 1 | 18 | 3.65 |
Heng-Chang Xiong | 2 | 3 | 0.36 |
Yi Xiao | 3 | 62 | 12.53 |
Weili Guan | 4 | 43 | 10.84 |
Meng Wang | 5 | 3 | 0.36 |
Richang Hong | 6 | 4791 | 176.47 |
Zhiyong Li | 7 | 5 | 1.10 |