Compact Generalized Non-local Network

TL;DR

This paper introduces a generalized non-local module that models inter-channel interactions efficiently, improving fine-grained object recognition and video classification performance.

Contribution

It extends the non-local module to include channel interactions using a compact Taylor expansion, enabling faster and low-complexity computation.

Findings

Improved accuracy on fine-grained object recognition tasks.

Enhanced video classification performance.

Efficient implementation with low computational complexity.

Abstract

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.