CBNet: A Novel Composite Backbone Network Architecture for Object Detection

9 Sep 2019Yudong LiuYongtao WangSiwei WangTingTing LiangQijie ZhaoZhi TangHaibin Ling

In existing CNN based detectors, the backbone network is a very important component for basic feature extraction, and the performance of the detectors highly depends on it. In this paper, we aim to achieve better detection performance by building a more powerful backbone from existing backbones like ResNet and ResNeXt... (read more)

PDF Abstract

Evaluation Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK COMPARE
Instance Segmentation COCO test-dev Cascade Mask R-CNN (ResNeXt152, CBNet) mask AP 43.3% # 2
Object Detection COCO test-dev Cascade Mask R-CNN (Triple-ResNeXt152, multi-scale) box AP 53.3 # 1
Object Detection COCO test-dev Cascade Mask R-CNN (Triple-ResNeXt152, multi-scale) AP50 71.9 # 1
Object Detection COCO test-dev Cascade Mask R-CNN (Triple-ResNeXt152, multi-scale) AP75 58.5 # 1
Object Detection COCO test-dev Cascade Mask R-CNN (Triple-ResNeXt152, multi-scale) APS 35.5 # 1
Object Detection COCO test-dev Cascade Mask R-CNN (Triple-ResNeXt152, multi-scale) APM 55.8 # 1
Object Detection COCO test-dev Cascade Mask R-CNN (Triple-ResNeXt152, multi-scale) APL 66.7 # 1