Incorporating Task-Agnostic Information in Task-Based Active Learning Using a Variational Autoencoder
Incorporating Task-Agnostic Information in Task-Based Active Learning Using a Variational Autoencoder
复制标题
DOI：
10.25080/majora-212e5952-011
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
C. Godwin;Meekail Zain;Nathan Safir;Bella Humphrey;Shannon Quinn
中科院分区：
文献类型：
--
作者：
C. Godwin;Meekail Zain;Nathan Safir;Bella Humphrey;Shannon Quinn
- 收集数据通常比标记数据更容易，成本更低。主动学习（AL）（[Set 09]）通过选择哪些未标记的数据最好接下来标记来应对这个问题。标准方法利用任务感知AL，它基于训练的监督模型识别信息样本。任务不可知的AL忽略任务模型，而是根据数据集的学习属性进行选择。我们试图将这些方法联合收割机和测量的贡献，将任务不可知的信息纳入标准AL，怀疑额外的信息中的任务不可知的功能可能会改善选择过程。我们使用ResNet分类器在各种AL方法上测试了这一点，其中包含和不包含来自变分自动编码器（VAE）的无监督信息。虽然结果没有显示出显着的改善，我们调查的收购功能的影响，并建议潜在的方法来扩展工作。
—It is often much easier and less expensive to collect data than to label it. Active learning (AL) ([Set09]) responds to this issue by selecting which unlabeled data are best to label next. Standard approaches utilize task-aware AL, which identifies informative samples based on a trained supervised model. Task-agnostic AL ignores the task model and instead makes selections based on learned properties of the dataset. We seek to combine these approaches and measure the contribution of incorporating task-agnostic information into standard AL, with the suspicion that the extra information in the task-agnostic features may improve the selection process. We test this on various AL methods using a ResNet classifier with and without added unsupervised information from a variational autoencoder (VAE). Although the results do not show a significant improvement, we investigate the effects on the acquisition function and suggest potential approaches for extending the work.