发表机构
Towson University; University of Maryland, Baltimore County（陶森大学; 马里兰大学巴尔的摩县分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究通过对比经典CNN、现代CNN、纯注意力及混合模型在格陵兰冰盖图像分类中的表现，发现卷积模型在准确率和平衡性能上最优，强调架构归纳偏置需与冰冻圈数据特征对齐，复杂度增加不必然提升可靠性。
AI 中文摘要
基于注意力的深度学习的最新进展推动了其在遥感图像分类中的应用；然而，对于冰冻圈图像，其表面状态以细粒度纹理和类别不平衡为主导，这些方法的益处仍不明确。在本工作中，我们重新审视了一个格陵兰冰盖图像基准数据集，该数据集先前被认为有利于卷积神经网络（CNNs），以检验现代基于注意力的和混合架构是否提高了类别级别的可靠性。我们在相同的训练和评估协议下，对经典CNN（AlexNet）、现代CNN（ConvNeXt-Tiny）、纯基于注意力的模型（Swin-Tiny）以及混合卷积-注意力模型（CoAtNet-0）进行了受控比较。结果表明，AlexNet在准确率和宏平均F1衡量的平衡性能上达到最高，而ConvNeXt-Tiny表现出最高的宏平均AUC，表明其具有较强的类别可分性但最终决策质量一致性较差。类别级别的分析显示，混合架构提高了稀有且结构上独特的表面类别的召回率，而卷积模型在纹理主导的类别上仍然更可靠。这些发现强调了将架构归纳偏置与冰冻圈数据特征对齐的重要性，并表明增加模型复杂度并不一定转化为冰盖表面分类可靠性的提升。
英文摘要
Recent advances in attention-based deep learning have motivated their adoption for remote sensing image classification; however, their benefits for cryospheric imagery, where surface states are dominated by fine-grained textures and class imbalance, remain unclear. In this work, we revisit a benchmark Greenland Ice Sheet image dataset, previously shown to favor convolutional neural networks (CNNs), to examine whether modern attention-based and hybrid architectures improve class-wise reliability. We conduct a controlled comparison between a classical CNN (AlexNet), a modern CNN (ConvNeXt-Tiny), a pure attention-based model (Swin-Tiny), and a hybrid convolution-attention model (CoAtNet-0) under identical training and evaluation protocols. Results show that AlexNet achieves the highest accuracy and the strongest balanced performance as measured by macro-averaged F1, while ConvNeXt-Tiny exhibits the highest macro-averaged AUC, indicating strong class separability but less consistent final decision quality. Class-wise analysis reveals that hybrid architectures improve recall for rare and structurally distinct surface classes, whereas convolutional models remain more reliable for texture-dominated categories. These findings highlight the importance of aligning architectural inductive bias with cryospheric data characteristics and suggest that increased model complexity does not necessarily translate to improved reliability for ice-sheet surface classification.
CommentsAccepted at IEEE IGARSS 2026, 5 pages, 3 figures
