1st place in the Satellite Image Change Detection Challenge hosted by SenseTime.

Given two images of the same scene acquired at different times, we are required to mark the changed and unchanged areas. Moreover, as for the changed areas, we need to annotate their detailed semantic masks.

The change detection task in this competition can be decomposed into two sub-tasks:

• binary segmentation of changed and unchanged areas.
• semantic segmentation of changed areas.

Download code: f3qq

The core practice is using self-distillation strategy to assign pseudo labels to unchanged areas.

Specifically, in our experiments, predictions of five HRNet-based segmentation models are ensembled, serving as pseudo labels of unchanged areas.

The overall training process can be summarized as:

• Training multiple large segmentation models.
• Ensembling their predictions on unchanged areas.
• Training a smaller model with both labeled and pseudo labeled areas.

For more details, please refer to the technical report and presentation.