InceptionMamba：一种采用大频带卷积与瓶颈 Mamba 的高效混合网络
InceptionMamba: An Efficient Hybrid Network with Large Band Convolution and Bottleneck Mamba
AI总结：
本文提出 InceptionMamba 混合骨干网络，用正交频带卷积增强局部空间建模，并以瓶颈 Mamba 捕获全局上下文，在分类和下游任务中实现更优精度与效率。
摘要：
在卷积神经网络家族中，InceptionNeXt 已在图像分类和多项下游任务中展现出出色的竞争力。然而，它建立在并行一维条状卷积之上，因此在沿不同维度捕获空间依赖关系方面能力有限，也未能充分挖掘局部邻域中的空间建模。此外，卷积运算固有的局部性约束不利于有效的全局上下文建模。为克服这些限制，本研究提出了一种名为 InceptionMamba 的新型骨干架构。更具体地说，在 InceptionMamba 中，传统的一维条状卷积被正交频带卷积取代，以实现具有内聚性的空间建模。此外，全局上下文建模可通过瓶颈 Mamba 模块实现，从而促进增强的跨通道信息融合并扩大感受野。在分类和各种下游任务上的大量评估表明，所提出的 InceptionMamba 达到了最先进性能，并具有更优的参数与计算效率。源代码将在 https://github.com/Wake1021/InceptionMamba 提供。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
