Diagnosing Ensemble Few-Shot Classifiers
This addresses the difficulty in understanding and enhancing performance for users of ensemble few-shot classifiers, though it is incremental as it builds on existing methods with specific improvements.
The paper tackles the problem of diagnosing and improving ensemble few-shot classifiers by proposing FSLDiagnotor, a visual analysis method that selects optimal base learners and shots, resulting in accuracy increases of 12% and 21% in case studies.
The base learners and labeled samples (shots) in an ensemble few-shot classifier greatly affect the model performance. When the performance is not satisfactory, it is usually difficult to understand the underlying causes and make improvements. To tackle this issue, we propose a visual analysis method, FSLDiagnotor. Given a set of base learners and a collection of samples with a few shots, we consider two problems: 1) finding a subset of base learners that well predict the sample collections; and 2) replacing the low-quality shots with more representative ones to adequately represent the sample collections. We formulate both problems as sparse subset selection and develop two selection algorithms to recommend appropriate learners and shots, respectively. A matrix visualization and a scatterplot are combined to explain the recommended learners and shots in context and facilitate users in adjusting them. Based on the adjustment, the algorithm updates the recommendation results for another round of improvement. Two case studies are conducted to demonstrate that FSLDiagnotor helps build a few-shot classifier efficiently and increases the accuracy by 12% and 21%, respectively.