Pos-DANet: A dual-branch awareness network for small object segmentation within high-resolution remote sensing images

The more detailed and accurate earth observation has been made driven by the progress of satellites and sensors optical photography technology, which poses both an opportunity and a challenge to small object segmentation task. However, the inherent difficulty and inadequate consideration still make small object segmentation task inevitably encounter a performance gain bottleneck. We analyze the longstanding but underestimated challenges in this task and give a peer-to-peer solution to response them. Specifically, we design a dual-branch awareness structure dedicated to small object segmentation, named Pos-DANet, which is composed with a small object activation branch and a fuzzy refinement branch. The small object activation branch is used to aware the small objects and avoid the negative influence of redundant background. The fuzzy refinement branch utilizes the fuzzy modeling to improve the segmentation accuracy of small objects. These two branches work collaboratively to make the whole structure to focus more on small objects and achieve satisfying segmentation results. Finally, we propose a hierarchical unbiased loss to eliminate the bias against small objects in the regression process. Extensive experiments demonstrated that Pos-DANet exhibits a higher qualitative and quantitative performance than the advanced methods within small objects, which achieves the best results in mIoU (71.12 %, 83.33 %) and sIoU (63.23 %, 68.89 %) on two datasets.