Multiple Instance Hybrid Estimator for Learning Target Signatures
This addresses a domain-specific challenge in hyperspectral imaging for applications like remote sensing, where obtaining accurate target signatures is difficult, though it appears incremental as it builds on existing signature-based detectors.
The paper tackles the problem of estimating discriminative target signatures for hyperspectral target detection when precise labels are unavailable, by proposing a multiple instance learning approach that maximizes hybrid sub-pixel detector response, and demonstrates effectiveness through simulated and real experiments.
Signature-based detectors for hyperspectral target detection rely on knowing the specific target signature in advance. However, target signature are often difficult or impossible to obtain. Furthermore, common methods for obtaining target signatures, such as from laboratory measurements or manual selection from an image scene, usually do not capture the discriminative features of target class. In this paper, an approach for estimating a discriminative target signature from imprecise labels is presented. The proposed approach maximizes the response of the hybrid sub-pixel detector within a multiple instance learning framework and estimates a set of discriminative target signatures. After learning target signatures, any signature based detector can then be applied on test data. Both simulated and real hyperspectral target detection experiments are shown to illustrate the effectiveness of the method.