MMDetection/configs/detectors

• DetectoRS
• • Introduction
  • Results and Models

DetectoRS

Introduction

We provide the config files for DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution.

@article{qiao2020detectors,
  title={DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution},
  author={Qiao, Siyuan and Chen, Liang-Chieh and Yuille, Alan},
  journal={arXiv preprint arXiv:2006.02334},
  year={2020}
}

Results and Models

DetectoRS includes two major components:

• Recursive Feature Pyramid (RFP).
• Switchable Atrous Convolution (SAC).

They can be used independently.
Combining them together results in DetectoRS.
The results on COCO 2017 val are shown in the below table.

Method	Detector	Lr schd	Mem (GB)	Inf time (fps)	box AP	mask AP	Download
RFP	Cascade + ResNet-50	1x	7.5	-	44.8		model | log
SAC	Cascade + ResNet-50	1x	5.6	-	45.0		model | log
DetectoRS	Cascade + ResNet-50	1x	9.9	-	47.4		model | log
RFP	HTC + ResNet-50	1x	11.2	-	46.6	40.9	model | log
SAC	HTC + ResNet-50	1x	9.3	-	46.4	40.9	model | log
DetectoRS	HTC + ResNet-50	1x	13.6	-	49.1	42.6	model | log

Note: This is a re-implementation based on MMDetection-V2.
The original implementation is based on MMDetection-V1.