Active Learning Classification from a Signal Separation Perspective
This work addresses classification challenges in machine learning, particularly for hyperspectral data with overlapping distributions, but appears incremental as it builds on existing active learning methods.
The paper tackled the problem of classification by proposing a novel clustering and classification framework inspired by signal separation principles, which efficiently identifies class supports even with overlapping distributions, and validated it on hyperspectral datasets Salinas and Indian Pines, showing competitive performance with state-of-the-art active learning algorithms using a very small subset of training data.
In machine learning, classification is usually seen as a function approximation problem, where the goal is to learn a function that maps input features to class labels. In this paper, we propose a novel clustering and classification framework inspired by the principles of signal separation. This approach enables efficient identification of class supports, even in the presence of overlapping distributions. We validate our method on real-world hyperspectral datasets Salinas and Indian Pines. The experimental results demonstrate that our method is competitive with the state of the art active learning algorithms by using a very small subset of data set as training points.