用带状卷积和Mamba模块提升图像模型的局部与全局建模能力
InceptionMamba: An Efficient Hybrid Network with Large Band Convolution and Bottleneck Mamba
- 用正交带状卷积替代传统一维条带卷积，增强空间建模
- 引入瓶颈Mamba模块，实现全局上下文捕捉与跨通道融合
- 在分类和下游任务中表现领先，参数与计算量更少
在卷积神经网络中，InceptionNeXt在图像分类及多个下游任务中表现出色。然而，其基于并行一维条带卷积的结构受限于不同维度的空间依赖捕获能力不足，且难以充分挖掘局部邻域的空间建模潜力。此外，卷积固有的局部性限制了全局上下文的有效建模。为此，本文提出新型主干架构InceptionMamba：将传统一维条带卷积替换为正交带状卷积，以实现连贯的空间建模；同时引入瓶颈Mamba模块，实现全局上下文建模，促进跨通道信息融合并扩大感受野。在分类及多种下游任务上的大量实验表明，InceptionMamba在保持优异性能的同时，具备更强的参数与计算效率，达到当前最优水平。源代码将在https://github.com/Wake1021/InceptionMamba发布。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。