arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1902.03545cs.LGcs.AIstat.ML
收藏

Task2Vec:面向元学习的任务嵌入

Task2Vec: Task Embedding for Meta-Learning

UCLA(加州大学洛杉矶分校);AWS(亚马逊云服务);UMass(马萨诸塞大学);UCI(加州大学尔湾分校);Caltech(加州理工学院)

Alessandro Achille, Michael Lam, Rahul Tewari, Avinash Ravichandran, Subhransu Maji, Charless Fowlkes, Stefano Soatto, Pietro Perona

摘要:

我们介绍了一种方法来提供矢量表示的视觉分类任务,可以用来推理这些任务的性质和它们之间的关系。给定一个带有地面真实标签的数据集和在这些标签上定义的损失函数,我们通过“探测网络”处理图像,并根据与探测网络参数相关的Fisher信息矩阵的估计值计算嵌入。这提供了任务的固定维度嵌入,其独立于诸如类的数量之类的细节,并且不需要对类标签语义的任何理解。我们证明了这种嵌入能够预测任务相似性,这些相似性与我们对不同视觉任务之间的语义和分类关系的直觉相匹配(例如,基于对不同类型植物进行分类的任务是相似的),我们还证明了该框架对于为新任务选择预训练特征提取器的元任务的实用价值。我们提出了一个简单的元学习框架,用于学习嵌入的度量,该度量能够预测哪些特征提取器将表现良好。选择具有任务嵌入的特征提取器获得接近最佳可用特征提取器的性能,同时成本大大低于对所有可用特征提取器进行穷举训练和评估。

英文摘要:

We introduce a method to provide vectorial representations of visual classification tasks which can be used to reason about the nature of those tasks and their relations. Given a dataset with ground-truth labels and a loss function defined over those labels, we process images through a "probe network" and compute an embedding based on estimates of the Fisher information matrix associated with the probe network parameters. This provides a fixed-dimensional embedding of the task that is independent of details such as the number of classes and does not require any understanding of the class label semantics. We demonstrate that this embedding is capable of predicting task similarities that match our intuition about semantic and taxonomic relations between different visual tasks (e.g., tasks based on classifying different types of plants are similar) We also demonstrate the practical value of this framework for the meta-task of selecting a pre-trained feature extractor for a new task. We present a simple meta-learning framework for learning a metric on embeddings that is capable of predicting which feature extractors will perform well. Selecting a feature extractor with task embedding obtains a performance close to the best available feature extractor, while costing substantially less than exhaustively training and evaluating on all available feature extractors.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑