Abstract | ||
---|---|---|
•We analyze the limitation of the classification head in one-stage detectors, which fills the gap in the literature.•We explain the classifier's limitation by visualizing its representations and analyzing its robustness to the scene context.•The findings give insights to design location-aware multi-dilation module (LAMD) in the classifiers for robust detection.•Experiments on MS COCO across various detectors with different backbones show that our method can achieve higher performance. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1016/j.patcog.2020.107334 | Pattern Recognition |
Keywords | DocType | Volume |
Object detetion,Classification,Localization,Feature visualization,Receptive field | Journal | 105 |
Issue | ISSN | Citations |
1 | 0031-3203 | 3 |
PageRank | References | Authors |
0.41 | 0 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Chen Qiang | 1 | 3 | 1.08 |
Peisong Wang | 2 | 50 | 8.80 |
Cheng Anda | 3 | 3 | 1.76 |
Wanguo Wang | 4 | 3 | 0.41 |
Yifan Zhang | 5 | 512 | 30.27 |
Jian Cheng | 6 | 1327 | 115.72 |