MultiAttenGastro：用于胃肠内窥镜分类的多维注意力增强框架
MultiAttenGastro: Multi-Dimensional Attention Augmentation for Gastrointestinal Endoscopy Classification
浏览论文内容
中文总结 AI 辅助
该研究提出即插即用的多维注意力框架MultiAttenGastro，经跨数据集评估发现其效果与表征差距相关，仅在大差距场景下能提升多数骨干网络的胃肠内窥镜分类性能。
中文摘要 AI 辅助
自动胃肠（GI）内窥镜分类需要能够在不同模态和类别分布间泛化的模型，这类模型通常与自然图像预训练存在较大差异。我们提出MultiAttenGastro，这是一种即插即用的注意力框架，包含并行的1维通道、2维空间和3维上下文头；并在五个公开GI数据集上，对八个CNN和Transformer骨干网络开展了首次系统性跨数据集评估，共进行80次骨干-数据集运行。我们发现注意力的有效性并非通用，而是与ImageNet特征和目标分布之间的表征差距相关：MultiAttenGastro在Kvasir-Capsule（14类WCE，差距较大）上提升了8个骨干网络中的6个，最佳宏观F1值达98.33%；在差距较小的Kvasir-v2基准上，其效果均为负面（8个骨干网络提升数为0）；在差距中等的数据集上则呈现混合结果。对最优情况（Kvasir-Capsule、ConvNeXt-Tiny）的五折消融实验表明，该提升在方向上一致，但统计上不具备决定性（配对t检验：p=0.47；Wilcoxon检验：p=0.63）；且单个注意力头单独使用时并非均有益，仅组合使用才能产生正向平均效果。中心核对齐（CKA）分析将该模式与表征冗余度关联：在大领域差距下，头间CKA值低与框架仅有的一致增益重合；而在小差距下，高冗余度与框架的损失重合。我们报告这些结果（包括非显著边际），旨在说明多维注意力在胃肠内窥镜分类中何时及为何有效，而非声称MultiAttenGastro是绝对更优的架构选择。
英文摘要
Automated gastrointestinal (GI) endoscopy classification requires models that generalize across diverse modalities and class distributions, often far from natural-image pretraining. We propose MultiAttenGastro, a plug-and-play attention framework with parallel 1-D channel, 2-D spatial, and 3-D contextual heads, and present the first systematic cross-dataset evaluation across eight CNN and transformer backbones on five public GI datasets (80 backbone--dataset runs). We find that attention effectiveness is not universal but tracks the representational gap between ImageNet features and the target distribution: MultiAttenGastro improves 6 of 8 backbones on Kvasir-Capsule (14-class WCE, large gap; best macro F1 98.33\%), is uniformly negative on the small-gap Kvasir-v2 benchmark (0/8), and shows mixed outcomes on datasets with intermediate gap. Five-seed ablation on the strongest case (Kvasir-Capsule, ConvNeXt-Tiny) shows this improvement is directionally consistent, but not statistically decisive (paired $t$: $p=0.47$; Wilcoxon: $p=0.63$), and that individual attention heads are not uniformly beneficial in isolation only their combination yields a positive mean effect. Centered Kernel Alignment (CKA) analysis links this pattern to representational redundancy: low inter-head CKA under large domain gaps coincides with the framework's only consistent gains, while high redundancy under small gaps coincides with its losses. We report these results, including the non-significant margins, as evidence for when and why multi-dimensional attention helps GI endoscopy classification, rather than as a claim that MultiAttenGastro is a strictly superior architectural choice.
发表机构
- Sardar Vallabhbhai National Institute of Technology（萨达尔·瓦拉巴伊·国家理工学院）
- Swasthyam Gastro and Liver Hospital（斯瓦斯蒂亚姆胃肠肝病医院）
- Norwegian University of Science and Technology（挪威科技大学）
机构由 AI 辅助整理，请以论文原文为准。
