Active Learning via Multi-View and Local Proximity Co-Regularization for Hyperspectral Image Classification

Abstract

Abstract-A novel co-regularization framework for active learning is proposed for hyperspectral image classification. The first regularizer explores the intrinsic multi-view information embedded in the hyperspectral data. By adaptively and quantitatively measuring the disagreement level, it focuses only on samples with high uncertainty and builds a contention pool which is a small subset of the overall unlabeled data pool, thereby mitigating the computational cost. The second regularizer is based on the "consistency assumption" and designed on a spatial or the spectral based manifold space. It serves to further focus on the most informative samples within the contention pool by penalizing rapid changes in the classification function evaluated on proximally close samples in a local region. Such changes may be due to the lack of capability of the current learner to describe the unlabeled data. Incorporating manifold learning into the active learning process enforces the clustering assumption and avoids the degradation of the distance measure associated with the original high-dimensional spectral features. One spatial and two local spectral embedding methods are considered in this study, in conjunction with the support vector machine (SVM) classifier implemented with a radial basis function (RBF) kernel. Experiments show excellent performance on AVIRIS and Hyperion hyperspectral data as compared to random sampling and the state-of-the-art SVM SIMPLE .

Critical class oriented active learning for hyperspectral image classification

“…Also, manual selection of the training set is often subjective and tends to induce redundancy into the classifier [1][2][3]. Thus, recently there has been increasing interest in active learning (AL) in remote sensing [4][5][6][7] to improve the selection and utilization of training data. AL integrates data acquisition with the classifier design by iteratively learning from the unlabeled data to provide the advice for the next query.…”

Active Learning: Any Value for Classification of Remotely Sensed Data?

“…Approaches based on a committee of models have also been considered, either based on models trained on sample subsets of L (e.g. Entropy Query-by-Bagging (EQB) [30]) or on subsets of the d-dimensional feature space (Multi-view [31], [32]). See Fig.…”

3D-Gabor Inspired Multiview Active Learning for Spectral-Spatial Hyperspectral Image Classification

“…This family includes several representative methods, such as margin sampling (MS) [30], multiclass level uncertainty (MCLU) [31] and significance space construction (SSC) [32]; (3) Committee-based heuristic, which qualifies the uncertainty of samples by using the inconsistent hypothesis between each committee. Typical methods include the normalized entropy query-by-bagging (nEQB) [33], maximum disagreement (MD)-based criteria [34] and adaptive maximum disagreement (AMD) [35]. The traditional single-view AL (SVAL) is usually based on the first two families, and a new branch of AL named multiview AL (MVAL), which adhered to the principles of the third family with the information of multiple views, has attracted considerable interest over the past few years [36].…”

“…To solve the problem, we propose a three-dimensional Gabor (3D-Gabor) and cube assessment based method to generate the multiple views without augmenting the dimensions. As to the second issue, various query selection methods have been proposed in the last decade [24,34,35]. They provide the simple and direct approaches to utilize the nature of disagreement between multiple views.…”