Multi-model ensemble with rich spatial information for object detection

作者：

Highlights：

• Ensemble learning improves the performance of object detection and achieves the mAP of state-of-the-art detectors.

• The combination of context modeling and dilated convolution ensures the detection speed.

• The proposed multi-scale feature fusion module confers a clear improvement to the detector.

• The proposed ensemble modes demonstrate the effectiveness of ensemble learning in the field of object detection.

摘要

•Ensemble learning improves the performance of object detection and achieves the mAP of state-of-the-art detectors.•The combination of context modeling and dilated convolution ensures the detection speed.•The proposed multi-scale feature fusion module confers a clear improvement to the detector.•The proposed ensemble modes demonstrate the effectiveness of ensemble learning in the field of object detection.

论文关键词：Ensemble learning,Object detection,Dilated convolution,Feature fusion

论文评审过程：Received 8 February 2019, Revised 31 August 2019, Accepted 29 October 2019, Available online 31 October 2019, Version of Record 8 November 2019.

论文官网地址：https://doi.org/10.1016/j.patcog.2019.107098