Learning to Aggregate Multi-Scale Context for Instance Segmentation in Remote Sensing Images

The task of instance segmentation in remote sensing images, aiming at performing per-pixel labeling of objects at the instance level, is of great importance for various civil applications. Despite previous successes, most existing instance segmentation methods designed for natural images encounter sharp performance degradations when they are directly applied to top-view remote sensing images. Through careful analysis, we observe that the challenges mainly come from the lack of discriminative object features due to severe scale variations, low contrasts, and clustered distributions. In order to address these problems, a novel context aggregation network (CATNet) is proposed to improve the feature extraction…

• NN
  National Natural Science Foundation of China

  Award: 42371366
• FR
  Fundamental Research Funds for the Central Universities

  Award: 2042023kfyq04