提出新型变压器模型，高效去除遥感图像云层干扰
ATT-CR: Adaptive Triangular Transformer for Cloud Removal
- 用三角注意力结构降低计算复杂度至O(N)
- 自适应区分云与清晰像素，减少干扰信息传播
- 在多个基准上表现优于现有方法，适合遥感图像处理
云层去除旨在准确重建遥感图像中被云遮挡的地表物体。现有基于Transformer的方法虽通过自注意力有效建模长程依赖，但存在两个问题：1）自注意力计算复杂度高，限制可扩展性；2）在注意力计算中将云和清晰像素均视为有效，导致后续层引入干扰，影响性能。为此，本文提出自适应三角形Transformer（ATT-CR），有效降低计算成本并减少云像素干扰。其核心由两部分组成：三角注意力（TAN）和特征选择门控模块（FSGM）。TAN采用下三角和上三角矩阵近似Softmax注意力，将计算复杂度降至O(N)，显著降低开销；FSGM与TAN协同工作，自适应区分云与清晰特征，抑制无效信息进入后续层。在多个云层去除基准数据集上的实验表明，ATT-CR在性能上优于现有方法。
原文摘要 · Abstract (English)
Cloud removal aims to accurately reconstruct the ground objects obscured by clouds in remote sensing images. Existing Transformer-based methods utilizing self-attention have shown impressive results by effectively modeling long-range dependencies in cloudy images. However, they suffer from the following issues: 1) the high computational complexity of self-attention limits scalability; 2) treating both cloudy and clean pixels as valid within the attention computation brings disturbances in subsequent layers, leading to suboptimal performance. To address these challenges, we propose the Adaptive Triangular Transformer for Cloud Removal (ATT-CR), a model that effectively reduces computational costs and mitigates interference from cloudy pixels. Specifically, it consists of two core components: Triangular Attention (TAN) and Feature Selected Gating Module (FSGM). TAN employs lower and upper triangular matrices to approximate Softmax attention with O(N) computational complexity, significantly reducing the computational costs. The FSGM, on the other hand, integrates with TAN to adaptively distinguish between cloudy and clean features, which minimizes the introduction of invalid information into subsequent layers. Extensive experiments on cloud removal benchmarks demonstrate that ATT-CR delivers superior performance compared to existing methods.
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。