· 2018
Non-local Neural Networks
- 11,253citations
- 2018year
Short summary
Non-local operations, a new neural network building block, capture long-range dependencies by computing feature responses as a weighted sum of all positions, outperforming existing methods on video classification and improving static image recognition tasks.
AI-generated from the title and abstract; the full text is not read.
Key points
- Introduces non-local operations as a new neural network building block.
- Non-local operations compute feature responses as a weighted sum of features at all positions.
- Models using non-local operations compete with or outperform state-of-the-art on video classification (Kinetics, Charades).
- Non-local models improve object detection, segmentation, and pose estimation on static images (COCO).
AI-generated from the title and abstract; the full text is not read.
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 .
The authors' abstract, as published at the source., 2018 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionComputer Science