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

by   Can Yaras, et al.

Modern deep neural networks (DNNs) achieve highly accurate results for many recognition tasks on overhead (e.g., satellite) imagery. One challenge however is visual domain shifts (i.e., statistical changes), which can cause the accuracy of DNNs to degrade substantially and unpredictably when tested 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 show that modern DNNs can become largely invariant 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 problem, we propose a simple real-time unsupervised training augmentation technique, termed randomized histogram matching (RHM). We conduct experiments with two large public benchmark datasets for building segmentation and find that RHM consistently yields comparable performance to recent state-of-the-art unsupervised domain adaptation approaches despite being simpler and faster. RHM also offers substantially better performance than other comparably simple approaches that are widely-used in overhead imagery.


page 2

page 3

page 6

page 14


The Synthinel-1 dataset: a collection of high resolution synthetic overhead imagery for building segmentation

Recently deep learning - namely convolutional neural networks (CNNs) - h...

SIMPL: Generating Synthetic Overhead Imagery to Address Zero-shot and Few-Shot Detection Problems

Recently deep neural networks (DNNs) have achieved tremendous success fo...

Adversarial Feature Augmentation for Unsupervised Domain Adaptation

Recent works showed that Generative Adversarial Networks (GANs) can be s...

Correlation Alignment for Unsupervised Domain Adaptation

In this chapter, we present CORrelation ALignment (CORAL), a simple yet ...

On the Robustness of Domain Adaption to Adversarial Attacks

State-of-the-art deep neural networks (DNNs) have been proved to have ex...

Incremental Adversarial Domain Adaptation for Continually Changing Environments

Continuous appearance shifts such as changes in weather and lighting con...