Hashed Binary Search Sampling for Convolutional Network Training with Large Overhead Image Patches
This addresses a domain-specific challenge in geospatial machine learning by reducing computational waste and enhancing generalization over wide geographical scenes, though it is incremental as it builds on existing sampling methods.
The paper tackles the problem of redundant and noisy training patches in large-scale overhead imagery by proposing a hashed binary search sampling framework, which accelerates training and improves model generalization for human settlement detection.
Very large overhead imagery associated with ground truth maps has the potential to generate billions of training image patches for machine learning algorithms. However, random sampling selection criteria often leads to redundant and noisy-image patches for model training. With minimal research efforts behind this challenge, the current status spells missed opportunities to develop supervised learning algorithms that generalize over wide geographical scenes. In addition, much of the computational cycles for large scale machine learning are poorly spent crunching through noisy and redundant image patches. We demonstrate a potential framework to address these challenges specifically, while evaluating a human settlement detection task. A novel binary search tree sampling scheme is fused with a kernel based hashing procedure that maps image patches into hash-buckets using binary codes generated from image content. The framework exploits inherent redundancy within billions of image patches to promote mostly high variance preserving samples for accelerating algorithmic training and increasing model generalization.