Current transformer-based change detection (CD) approaches either employ a pre-trained model trained on large-scale image classification ImageNet dataset or rely on first pre-training on another CD dataset and then fine-tuning on the target benchmark. This current strategy is driven by the fact that transformers typically require a large amount of training data to learn inductive biases, which is insufficient in standard CD datasets due to their small size. We develop an end-to-end CD approach with transformers that is trained from scratch and yet achieves state-of-the-art performance on four public benchmarks. Instead of using conventional self-attention that struggles to capture inductive biases when trained from scratch, our architecture utilizes a shuffled sparse-attention operation that focuses on selected sparse informative regions to capture the inherent characteristics of the CD data. Moreover, we introduce a change-enhanced feature fusion (CEFF) module to fuse the features from input image pairs by performing a per-channel re-weighting. Our CEFF module aids in enhancing the relevant semantic changes while suppressing the noisy ones. Extensive experiments on four CD datasets reveal the merits of the proposed contributions, achieving gains as high as 14.27\% in intersection-over-union (IoU) score, compared to the best-published results in the literature. Code is available at \url{https://github.com/mustansarfiaz/ScratchFormer}.

翻译：当前基于Transformer的变化检测（Change Detection, CD）方法通常采用在大规模图像分类数据集ImageNet上预训练的模型，或先在其他CD数据集上预训练再在目标基准上进行微调。此策略源于Transformer通常需要大量训练数据来学习归纳偏置，而标准CD数据集因规模较小难以满足这一需求。我们提出了一种端到端的CD方法，采用从零训练的Transformer架构，在四个公开基准上仍能达到最先进的性能。与从零训练时难以捕捉归纳偏置的传统自注意力机制不同，我们的架构采用了混洗稀疏注意力操作，聚焦于选定的稀疏信息区域以捕获CD数据的固有特征。此外，我们引入了一种变化增强特征融合（Change-Enhanced Feature Fusion, CEFF）模块，通过逐通道重加权来融合输入图像对的特征。CEFF模块有助于增强相关语义变化，同时抑制噪声变化。在四个CD数据集上的大量实验验证了所提出方法的有效性，相较于文献中已发表的最佳结果，交并比（Intersection-over-Union, IoU）得分最高提升了14.27%。代码已开源至\url{https://github.com/mustansarfiaz/ScratchFormer}。