Non-local Neural Networks

Code

• github.com/facebookresearch/video-nonlocal-net
  OfficialIn papercaffe2★ 0
• github.com/facebookresearch/SlowFast
  pytorch★ 7,320
• github.com/open-mmlab/mmaction2
  pytorch★ 4,959
• github.com/MIT-HAN-LAB/temporal-shift-module
  pytorch★ 2,196
• github.com/mirthai/csa-net
  pytorch★ 43
• github.com/tinymilky/RSANet
  pytorch★ 26
• github.com/tonysy/PyAction
  pytorch★ 17
• github.com/jpviguerasguillen/feedback-non-local-attention_fNLA
  tf★ 10
• github.com/jpviguerasguillen/feedback-non-local-attention-fnla
  tf★ 10
• github.com/changliu816/CV-paper-review
  tf★ 1

Abstract

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 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 non-local 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 is available at https://github.com/facebookresearch/video-nonlocal-net .

Tasks

Benchmark Results

Reproductions