iSAID: A Large-scale Dataset for Instance Segmentation in Aerial Images
This provides a benchmark for researchers working on aerial image analysis, addressing challenges like many instances and tiny objects, but it is incremental as it extends existing dataset efforts to a new domain.
The authors tackled the lack of a large-scale dataset for instance segmentation in aerial images by introducing iSAID, which includes 655,451 object instances across 2,806 high-resolution images, showing that existing methods like Mask R-CNN and PANet perform suboptimally on this data.
Existing Earth Vision datasets are either suitable for semantic segmentation or object detection. In this work, we introduce the first benchmark dataset for instance segmentation in aerial imagery that combines instance-level object detection and pixel-level segmentation tasks. In comparison to instance segmentation in natural scenes, aerial images present unique challenges e.g., a huge number of instances per image, large object-scale variations and abundant tiny objects. Our large-scale and densely annotated Instance Segmentation in Aerial Images Dataset (iSAID) comes with 655,451 object instances for 15 categories across 2,806 high-resolution images. Such precise per-pixel annotations for each instance ensure accurate localization that is essential for detailed scene analysis. Compared to existing small-scale aerial image based instance segmentation datasets, iSAID contains 15$\times$ the number of object categories and 5$\times$ the number of instances. We benchmark our dataset using two popular instance segmentation approaches for natural images, namely Mask R-CNN and PANet. In our experiments we show that direct application of off-the-shelf Mask R-CNN and PANet on aerial images provide suboptimal instance segmentation results, thus requiring specialized solutions from the research community. The dataset is publicly available at: https://captain-whu.github.io/iSAID/index.html