不依赖预训练模型，用新注意力机制实现97.23%卫星图像分类准确率
Balanced Multi-Task Attention for Satellite Image Classification: A Systematic Approach to Achieving 97.23% Accuracy on EuroSAT Without Pre-Training
- 设计平衡多任务注意力，融合空间与光谱特征提取
- 在EuroSAT上达97.23%准确率，所有类别超94.46%且误判差距24.25%
- 适合无预训练数据的遥感图像分类研究者参考
本文系统研究了适用于卫星地表分类的自定义卷积神经网络架构，在无需预训练模型的情况下于EuroSAT数据集上达到97.23%测试准确率。通过三阶段架构迭代（基础模型：94.30%，CBAM增强：95.98%，平衡多任务注意力：97.23%），识别并解决了卫星图像分类中的特定失效模式。核心贡献为一种新型平衡多任务注意力机制，结合坐标注意力（Coordinate Attention）进行空间特征提取与挤压-激励块（Squeeze-Excitation）进行光谱特征提取，并通过可学习融合参数统一。实验表明该参数自主收敛至约0.57，说明空间与光谱模态对卫星图像同等重要。采用渐进式DropBlock正则化（5%-20%按网络深度）和类别平衡损失加权以缓解过拟合与类别混淆不平衡。最终12层架构获得Cohen's Kappa 0.9692，所有类别准确率均超过94.46%，正确与错误预测间差距达24.25%。性能仅比微调后的ResNet-50（98.57%）低1.34%，且无需外部数据，验证了系统化架构设计在领域应用中的有效性。完整代码、训练模型与评估脚本均已公开。
原文摘要 · Abstract (English)
This work presents a systematic investigation of custom convolutional neural network architectures for satellite land use classification, achieving 97.23% test accuracy on the EuroSAT dataset without reliance on pre-trained models. Through three progressive architectural iterations (baseline: 94.30%, CBAM-enhanced: 95.98%, and balanced multi-task attention: 97.23%) we identify and address specific failure modes in satellite imagery classification. Our principal contribution is a novel balanced multi-task attention mechanism that combines Coordinate Attention for spatial feature extraction with Squeeze-Excitation blocks for spectral feature extraction, unified through a learnable fusion parameter. Experimental results demonstrate that this learnable parameter autonomously converges to alpha approximately 0.57, indicating near-equal importance of spatial and spectral modalities for satellite imagery. We employ progressive DropBlock regularization (5-20% by network depth) and class-balanced loss weighting to address overfitting and confusion pattern imbalance. The final 12-layer architecture achieves Cohen's Kappa of 0.9692 with all classes exceeding 94.46% accuracy, demonstrating confidence calibration with a 24.25% gap between correct and incorrect predictions. Our approach achieves performance within 1.34% of fine-tuned ResNet-50 (98.57%) while requiring no external data, validating the efficacy of systematic architectural design for domain-specific applications. Complete code, trained models, and evaluation scripts are publicly available.
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。