Compact Generalized Non-local Network

10/31/2018
by   Kaiyu Yue, et al.
0

The non-local module is designed for capturing long-range spatio-temporal dependencies in images and videos. Although having shown excellent performance, it lacks the mechanism to model the interactions between positions across channels, which are of vital importance in recognizing fine-grained objects and actions. To address this limitation, we generalize the non-local module and take the correlations between the positions of any two channels into account. This extension utilizes the compact representation for multiple kernel functions with Taylor expansion that makes the generalized non-local module in a fast and low-complexity computation flow. Moreover, we implement our generalized non-local method within channel groups to ease the optimization. Experimental results illustrate the clear-cut improvements and practical applicability of the generalized non-local module on both fine-grained object recognition and video classification. Code is available at: https://github.com/KaiyuYue/cgnl-network.pytorch.

READ FULL TEXT

page 1

page 7

page 8

research
06/09/2020

PNL: Efficient Long-Range Dependencies Extraction with Pyramid Non-Local Module for Action Recognition

Long-range spatiotemporal dependencies capturing plays an essential role...
research
05/19/2020

Associating Multi-Scale Receptive Fields for Fine-grained Recognition

Extracting and fusing part features have become the key of fined-grained...
research
12/24/2020

Global Context Networks

The Non-Local Network (NLNet) presents a pioneering approach for capturi...
research
07/26/2022

Large-displacement 3D Object Tracking with Hybrid Non-local Optimization

Optimization-based 3D object tracking is known to be precise and fast, b...
research
04/25/2019

GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond

The Non-Local Network (NLNet) presents a pioneering approach for capturi...
research
07/08/2020

Non-local modeling with asymptotic expansion homogenization of random materials

The aim of this study is to build a non-local homogenized model for thre...
research
07/06/2021

Poly-NL: Linear Complexity Non-local Layers with Polynomials

Spatial self-attention layers, in the form of Non-Local blocks, introduc...

Please sign up or login with your details

Forgot password? Click here to reset