ScaleMix: Intra- and inter-layer multiscale feature combination for change detection

Previous CD methods pay more attention to fuse inter-layer multiscale features, while ignores the intra-layer multiscale characteristics, which hurts the integrity of change objects with different sizes. In this paper, we propose to mix intra- and inter-layer multiscale features to generate more complete change regions. To realize intra-layer multiscale, we propose inception difference module (IDM), which employs convolutional filters with different sizes, absolute difference and residual connection to capture intra-layer multiscale characteristics. To capture inter-layer multiscale, we propose a \residual network refinement module (RNR) to fuse the features from the highest layer to the lowest layer and generate fine detailed change predictions. By considering the multiscale characteristics of intra- and inter-layer simultaneously, our method can capture complete changes of different sizes.