Non-local Neural Networks

CVPR 2018 Xiaolong WangRoss GirshickAbhinav GuptaKaiming He

Both convolutional and recurrent operations are building blocks that process one local neighborhood at a time. In this paper, we present non-local operations as a generic family of building blocks for capturing long-range dependencies... (read more)

PDF Abstract

Evaluation results from the paper

Task Dataset Model Metric name Metric value Global rank Compare
Object Detection COCO ResNeXt-152 + 1 NL block Bounding Box AP 45.0 # 8
Instance Segmentation COCO ResNeXt-152 + 1 NL block Average Precision 40.3% # 2
Keypoint Detection COCO Mask R-CNN + NL blocks (4 in head, 1 in backbone) Validation AP 66.5 # 6