Robust one-stage object detection with location-aware classifiers

作者：

Highlights：

• 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.

摘要

•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.

论文关键词：Object detetion,Classification,Localization,Feature visualization,Receptive field

论文评审过程：Received 15 July 2019, Revised 3 March 2020, Accepted 12 March 2020, Available online 13 March 2020, Version of Record 5 June 2020.

论文官网地址：https://doi.org/10.1016/j.patcog.2020.107334