期刊
IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS
卷 28, 期 9, 页码 3292-3306出版社
IEEE COMPUTER SOC
DOI: 10.1109/TVCG.2022.3182488
关键词
Visualization; Feature extraction; Predictive models; Training; Analytical models; Data models; Behavioral sciences; Few-shot learning; ensemble model; subset selection; matrix visualization; scatterplot
资金
- National Key R&D Program of China [2020YFB2104100]
- National Natural Science Foundation of China [U21A20469, 61936002]
- Institute Guo Qiang
- THUIBCS
- BLBCI
- Tsinghua-Kuaishou Institute of Future Media Data
In this paper, we propose a visual analysis method called FSLDiagnotor to address the issue of unsatisfactory performance in ensemble few-shot classifiers. We formulate the problem as sparse subset selection and develop two algorithms to recommend appropriate base learners and shots. The recommended results are explained and adjusted using matrix visualization and scatterplot. Two case studies demonstrate the effectiveness of FSLDiagnotor in building few-shot classifiers with improved accuracy.
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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据