Abstract | ||
---|---|---|
Recently, object detection has achieved great improvements due to deep CNNs. In this paper, we propose a novel proposal generation network named RFP-Net by mimicking human visual system for high-quality proposals generation. Specifically, RFP-Net takes receptive fields (RFs) as reference boxes to remove many hyper-parameters of anchor boxes that have large sensibility to object detection results. During network training, we select positive samples using an effective RF (eRF) rule instead of the Intersection-over-Union (IoU) rule, which only requires the centroid of a ground truth box to be within the eRF region. This renders RFP-Net learn the representation of region proposals not limited to be of a fixed range of scales and accurately localize the bounding boxes of region proposals around the eRF. RFP-Net also solves the imbalance problem between negative and positive samples with less computational cost. The proposed RFP-Net significantly improves multiply state-of-the-art two-stage and multi-stage detectors. For example, it achieves 43.1% AP by combined it with Cascade RCNN on MS COCO dataset, outperforming previous approaches. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1016/j.neucom.2020.04.106 | Neurocomputing |
Keywords | DocType | Volume |
Object detection,Convolutional neural network (CNN),Proposals generation,Receptive field,Effective receptive field | Journal | 405 |
ISSN | Citations | PageRank |
0925-2312 | 0 | 0.34 |
References | Authors | |
0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Lin Jiao | 1 | 3 | 2.44 |
Shengyu Zhang | 2 | 15 | 3.78 |
Shifeng Dong | 3 | 2 | 1.39 |
Hongqiang Wang | 4 | 0 | 0.34 |