Non-local Neural Networks

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. Inspired by the classical non-local means method [4] in computer...

Full description

Saved in:
Bibliographic Details
Published in2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition pp. 7794 - 7803
Main Authors Wang, Xiaolong, Girshick, Ross, Gupta, Abhinav, He, Kaiming
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2018
Subjects
Computational modeling
Computer vision
Convolution
Convolutional codes
Feedforward systems
Neural networks
Three-dimensional displays
Online AccessGet full text

Cover

More Information
Summary: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. Inspired by the classical non-local means method [4] in computer vision, our non-local operation computes the response at a position as a weighted sum of the features at all positions. This building block can be plugged into many computer vision architectures. On the task of video classification, even without any bells and whistles, our nonlocal models can compete or outperform current competition winners on both Kinetics and Charades datasets. In static image recognition, our non-local models improve object detection/segmentation and pose estimation on the COCO suite of tasks. Code will be made available.
ISSN:1063-6919
DOI:10.1109/CVPR.2018.00813