用状态空间模型提升显微图像分类效率与精度
MambaMIC: An Efficient Baseline for Microscopic Image Classification with State Space Models
- 双分支结构融合局部感知与全局依赖
- 在5个数据集上达到当前最好性能
- 适合需要高效高精度的医学图像分析场景
近年来，基于卷积神经网络（CNN）和Transformer的方法在显微图像分类（MIC）任务中取得了显著进展。然而，现有方法仍面临全局建模与高效计算之间的矛盾。虽然选择性状态空间模型（SSM）能以线性复杂度模拟长程依赖，但在显微图像分类中仍存在局部像素遗忘、通道冗余和局部感知不足等问题。为此，我们提出一种简单而高效的视觉主干网络MambaMIC。具体地，设计了局部-全局双分支聚合模块：MambaMIC Block，用于有效捕捉并融合局部连通性与全局依赖。在局部分支中，采用局部卷积捕获像素相似性，缓解局部遗忘问题并增强感知能力；在全局分支中，利用SSM提取全局依赖，同时通过局部感知增强滤波器减少通道冗余和局部遗忘。此外，还设计了特征调制交互聚合模块，实现深层特征交互与关键特征重定位。大量基准测试表明，MambaMIC在五个数据集上均取得当前最优性能。代码已公开于https://zs1314.github.io/MambaMIC。
原文摘要 · Abstract (English)
In recent years, CNN and Transformer-based methods have made significant progress in Microscopic Image Classification (MIC). However, existing approaches still face the dilemma between global modeling and efficient computation. While the Selective State Space Model (SSM) can simulate long-range dependencies with linear complexity, it still encounters challenges in MIC, such as local pixel forgetting, channel redundancy, and lack of local perception. To address these issues, we propose a simple yet efficient vision backbone for MIC tasks, named MambaMIC. Specifically, we introduce a Local-Global dual-branch aggregation module: the MambaMIC Block, designed to effectively capture and fuse local connectivity and global dependencies. In the local branch, we use local convolutions to capture pixel similarity, mitigating local pixel forgetting and enhancing perception. In the global branch, SSM extracts global dependencies, while Locally Aware Enhanced Filter reduces channel redundancy and local pixel forgetting. Additionally, we design a Feature Modulation Interaction Aggregation Module for deep feature interaction and key feature re-localization. Extensive benchmarking shows that MambaMIC achieves state-of-the-art performance across five datasets. code is available at https://zs1314.github.io/MambaMIC
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。