Randomized Histogram Matching: A Simple Augmentation for Unsupervised Domain Adaptation in Overhead Imagery

Can Yaras, Kaleb Kassaw, Bohao Huang, Kyle Bradbury, Jordan M. Malof

Research output: Contribution to journalArticlepeer-review


Modern deep neural networks (DNNs) are highly accurate on many recognition tasks for overhead (e.g., satellite) imagery. However, visual domain shifts (e.g., statistical changes due to geography, sensor, or atmospheric conditions) remain a challenge, causing the accuracy of DNNs to degrade substantially and unpredictably when testing on new sets of imagery. In this work, we model domain shifts caused by variations in imaging hardware, lighting, and other conditions as nonlinear pixel-wise transformations, and we perform a systematic study indicating that modern DNNs can become largely robust to these types of transformations, if provided with appropriate training data augmentation. In general, however, we do not know the transformation between two sets of imagery. To overcome this, we propose a fast real-time unsupervised training augmentation technique, termed randomized histogram matching (RHM). We conduct experiments with two large benchmark datasets for building segmentation and find that despite its simplicity, RHM consistently yields similar or superior performance compared to state-of-the-art unsupervised domain adaptation approaches, while being significantly simpler and more computationally efficient. RHM also offers substantially better performance than other comparably simple approaches that are widely used for overhead imagery.

Original languageEnglish
Pages (from-to)1988-1998
Number of pages11
JournalIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
StatePublished - 2023


  • Augmentation
  • domain adaptation
  • segmentation


Dive into the research topics of 'Randomized Histogram Matching: A Simple Augmentation for Unsupervised Domain Adaptation in Overhead Imagery'. Together they form a unique fingerprint.

Cite this