Spatially regularized active diffusion learning for high-dimensional images
This work addresses the challenge of labeling efficiency for high-dimensional image classification, which is incremental as it builds on diffusion geometry methods.
The paper tackles the problem of classifying high-dimensional images with minimal labeled data by proposing an active learning algorithm that uses spatially-regularized nonlinear diffusion geometry to sample from cluster cores, resulting in high-accuracy labelings with a very small number of training labels and state-of-the-art performance on real hyperspectral images.
An active learning algorithm for the classification of high-dimensional images is proposed in which spatially-regularized nonlinear diffusion geometry is used to characterize cluster cores. The proposed method samples from estimated cluster cores in order to generate a small but potent set of training labels which propagate to the remainder of the dataset via the underlying diffusion process. By spatially regularizing the rich, high-dimensional spectral information of the image to efficiently estimate the most significant and influential points in the data, our approach avoids redundancy in the training dataset. This allows it to produce high-accuracy labelings with a very small number of training labels. The proposed algorithm admits an efficient numerical implementation that scales essentially linearly in the number of data points under a suitable data model and enjoys state-of-the-art performance on real hyperspectral images.