Affiliation:
1. College of Computer Science and Technology China University of Petroleum Qingdao Shandong 266580 China
Abstract
AbstractFor existing object detectors, anchor‐based detectors lack global information, while anchor‐free detectors based on key points lack prior position information. The above issues may lead to the imbalance of detection accuracy and shape robustness. In order to alleviate the above contradictions, a new auxiliary network key point generation network (GPNet) is proposed to improve the performance of existing object detectors. Specifically, a series of key points are generated through ground truth (GT) supervision to obtain more global information. These key points generate pseudo boxes (Pbox) with learnable parameters. Pbox has more specific prior information than the manually designed candidate boxes. The scale information of the Pbox is embed into the classification branch to obtain a more appropriate receptive field. In addition, a novel improved strategy for label assignment by combining Pbox and GT to enhance the ability to classify positive and negative samples is proposed. Extensive experiments on multiple dense prediction methods validate the effectiveness of GPNet, with a performance improvement of 1.5 AP over baseline. In particular, with ResNext‐101‐64× 4d‐DCN as the backbone, this method achieves 49.5 AP with single‐scale testing.
Subject
Multidisciplinary,Modeling and Simulation,Numerical Analysis,Statistics and Probability