AdaDINO：用于高效遥感变化检测的冻结DINO的成对感知骨干内适配
AdaDINO: Pair-Aware In-Backbone Adaptation of Frozen DINO for Efficient Remote Sensing Change Detection
浏览论文内容
中文总结 AI 辅助
AdaDINO是一种成对感知的骨干内适配框架，通过CGLA、BSCS和CPGR模块优化冻结DINO，在4个遥感变化检测基准上实现了高效且性能更优的变化检测，在SYSU-CD上F1达85.29%且吞吐量提升1.41倍。
中文摘要 AI 辅助
DINO等视觉基础模型（VFMs）是针对单图像表示进行预训练的，而遥感变化检测需要对双时相对进行推理。现有的基于VFM的方法通常独立编码两幅图像，仅在之后进行比较，导致VFM骨干无法感知跨时间关系。为弥合这种不匹配，我们提出AdaDINO，一种成对感知的骨干内适配框架，为冻结的DINO编码器配备双时交互以实现高效变化检测。其核心组件是感知变化的门控局部适配（CGLA），在选定的冻结块后耦合两个流，并向它们注入符号相反的共享时间残差，增强真实变化响应的同时保留对中点。批量共享块选择（BSCS）通过保留可作为紧凑密集前馈网络（FFN）执行的批量共享通道块子集，进一步减少FFN计算。CGLA先验引导的细化（CPGR）解码器复用编码器侧的变化响应以实现由粗到细的预测。在四个遥感变化检测基准上的实验表明，AdaDINO相较于基于VFM的基线取得了有竞争力或更优的性能，在类别不可知的SYSU-CD数据集上增益最大。在移除62.5%的FFN隐藏宽度的情况下，AdaDINO在SYSU-CD上仍达到85.29%的F1值，同时实现1.41倍的吞吐量加速。代码将被发布。
英文摘要
Vision foundation models (VFMs) such as DINO are pretrained for single-image representation, whereas remote sensing change detection requires reasoning over a bi-temporal pair. Existing VFM-based methods usually encode the two images independently and compare them only afterward, leaving the VFM backbone unaware of cross-temporal relations. To bridge this mismatch, we present AdaDINO, a pair-aware in-backbone adaptation framework that equips a frozen DINO encoder with bi-temporal interaction for efficient change detection. Its core component, Change-aware Gated Local Adaptation (CGLA), couples the two streams after selected frozen blocks and injects a shared temporal residual into them with opposite signs, enhancing genuine change responses while preserving the pair midpoint. Batch-Shared Chunk Selection (BSCS) further reduces feed-forward network (FFN) computation by retaining a batch-shared subset of channel chunks that can be executed as a compact dense FFN. A CGLA-Prior-Guided Refinement (CPGR) decoder reuses encoder-side change responses for coarse-to-fine prediction. Experiments on four remote sensing change detection benchmarks show that AdaDINO achieves competitive or superior performance against VFM-based baselines, with the largest gain on the category-agnostic SYSU-CD dataset. With 62.5% of the FFN hidden width removed, AdaDINO still achieves an F1 score of 85.29% on SYSU-CD while delivering a 1.41$\times$ throughput speedup. The code will be released.
