用多感受野融合与交叉熵掩码，解决遥感变化检测的类别不平衡问题。
Multi-Receptive Field Ensemble with Cross-Entropy Masking for Class Imbalance in Remote Sensing Change Detection
- 设计多感受野集成结构，捕捉不同尺度的变化细节。
- 在S2Looking数据集上提升2.97%的F1分数，优于现有方法。
- 适合遥感图像分析、变化检测任务的研究者和工程师。
遥感变化检测（RSCD）是一项复杂任务，变化通常呈现不同尺度和方向。卷积神经网络（CNN）擅长捕捉局部空间模式，但受限于有限的感受野，无法建模全局语义；而变换器虽能建模长程依赖，却需大量数据，现有RSCD数据集规模不足以有效训练。为此，本文提出一种新架构：基于段一切（SAM）视觉基础模型，将编码器特征通过多感受野集成处理，以同时捕获局部与全局变化模式。设计了时空特征增强（STFE）模块以捕捉跨时相关系，构建解码器重建变化模式，并引入多尺度解码器融合注意力（MSDFA）融合多尺度信息，突出关键变化区域。集成中各分支在独立感受野下运行，实现从细粒度到粗粒度的层级建模。此外，提出一种新型交叉熵掩码（CEM）损失函数，有效缓解RSCD数据集中的类别不平衡问题。在四个数据集（Levir-CD、WHU-CD、CLCD、S2Looking）上均超越当前最优方法，在复杂S2Looking数据集上实现2.97%的F1分数提升。代码已开源：https://github.com/humza909/SAM-ECEM。
原文摘要 · Abstract (English)
Remote sensing change detection (RSCD) is a complex task, where changes often appear at different scales and orientations. Convolutional neural networks (CNNs) are good at capturing local spatial patterns but cannot model global semantics due to limited receptive fields. Alternatively, transformers can model long-range dependencies but are data hungry, and RSCD datasets are not large enough to train these models effectively. To tackle this, this paper presents a new architecture for RSCD which adapts a segment anything (SAM) vision foundation model and processes features from the SAM encoder through a multi-receptive field ensemble to capture local and global change patterns. We propose an ensemble of spatial-temporal feature enhancement (STFE) to capture cross-temporal relations, a decoder to reconstruct change patterns, and a multi-scale decoder fusion with attention (MSDFA) to fuse multi-scale decoder information and highlight key change patterns. Each branch in an ensemble operates on a separate receptive field to capture finer-to-coarser level details. Additionally, we propose a novel cross-entropy masking (CEM) loss to handle class-imbalance in RSCD datasets. Our work outperforms state-of-the-art (SOTA) methods on four change detection datasets, Levir-CD, WHU-CD, CLCD, and S2Looking. We achieved 2.97\% F1-score improvement on a complex S2Looking dataset. The code is available at: https://github.com/humza909/SAM-ECEM
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。