Designing Synthetic Overhead Imagery to Match a Target Geographic Region: Preliminary Results Training Deep Learning Models

Nair, Varun; Rhee, Paul; Yang, Jichen; Huang, Bo-Wun; Bradbury, Kyle; Malof, Jordan M.

doi:10.1109/igarss39084.2020.9324180

Cited by 1 publication

(1 citation statement)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For both the encoder and decoder, we drop the learning rate by one order of magnitude after 50 and 80 epochs. These settings are chosen to be nearly identical to that those in [44] -the only variation is that we additionally drop the learning rate after 80 epochs to ensure that the validation loss converges by the end of training.…”

Section: B Segmentation Model and Trainingmentioning

confidence: 99%

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

Yaras,

Kassaw,

Huang

et al. 2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

Self Cite

View full text Add to dashboard Cite

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 non-linear 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.

show abstract

Section: B Segmentation Model and Trainingmentioning

confidence: 99%