Semi-Supervised Classification and Segmentation on High Resolution Aerial Images
This work addresses post-disaster damage assessment for emergency responders, but it is incremental as it applies existing semi-supervised techniques to a new dataset.
The authors tackled the problem of damage assessment from high-resolution aerial images after Hurricane Harvey using a semi-supervised approach with pseudo labels, improving the baseline supervised loss significantly for classification and enhancing model generalization on validation and test splits.
FloodNet is a high-resolution image dataset acquired by a small UAV platform, DJI Mavic Pro quadcopters, after Hurricane Harvey. The dataset presents a unique challenge of advancing the damage assessment process for post-disaster scenarios using unlabeled and limited labeled dataset. We propose a solution to address their classification and semantic segmentation challenge. We approach this problem by generating pseudo labels for both classification and segmentation during training and slowly incrementing the amount by which the pseudo label loss affects the final loss. Using this semi-supervised method of training helped us improve our baseline supervised loss by a huge margin for classification, allowing the model to generalize and perform better on the validation and test splits of the dataset. In this paper, we compare and contrast the various methods and models for image classification and semantic segmentation on the FloodNet dataset.