InceptionMamba: An Efficient Hybrid Network with Large Band Convolution and Bottleneck Mamba

TL;DR

InceptionMamba introduces a novel hybrid convolutional architecture that enhances spatial and global context modeling, achieving state-of-the-art performance with improved efficiency in image classification and downstream tasks.

Contribution

The paper proposes InceptionMamba, replacing traditional strip convolutions with orthogonal band convolutions and incorporating a bottleneck Mamba module for better spatial and global context modeling.

Findings

Achieves state-of-the-art accuracy on image classification tasks.

Demonstrates superior parameter and computational efficiency.

Excels in various downstream tasks beyond classification.

Abstract

Within the family of convolutional neural networks, InceptionNeXt has shown excellent competitiveness in image classification and a number of downstream tasks. Built on parallel one-dimensional strip convolutions, however, it suffers from limited ability of capturing spatial dependencies along different dimensions and fails to fully explore spatial modeling in local neighborhood. Besides, inherent locality constraints of convolution operations are detrimental to effective global context modeling. To overcome these limitations, we propose a novel backbone architecture termed InceptionMamba in this study. More specifically, the traditional one-dimensional strip convolutions are replaced by orthogonal band convolutions in our InceptionMamba to achieve cohesive spatial modeling. Furthermore, global contextual modeling can be achieved via a bottleneck Mamba module, facilitating enhanced cross-channel information fusion and enlarged receptive field. Extensive evaluations on classification and various downstream tasks demonstrate that the proposed InceptionMamba achieves state-of-the-art performance with superior parameter and computational efficiency. The source code will be available at https://github.com/Wake1021/InceptionMamba.