论文标题
使用综合数据迈向上下文敏捷学习
Towards Context-Agnostic Learning Using Synthetic Data
论文作者
论文摘要
我们提出了一种新颖的学习设置，其中输入域是在两组产品上定义的地图的图像，其中一组完全决定了标签。我们为此设置得出了一种新的风险，该风险将分解为偏见和错误项，并且对真实标签表现出了令人惊讶的弱依赖性。受这些结果的启发，我们提出了一种算法，该算法旨在通过利用独立从设置进行采样的能力来最大程度地减少偏差项。我们将设置应用于视觉分类任务，我们的方法使我们能够在数据集中训练分类器，这些分类器完全由每个类的单个合成示例组成。在几种用于现实世界图像分类的标准基准上，我们在上下文不合时宜的环境中实现了良好的性能，对现实世界领域进行了良好的概括，而在没有我们的技术的情况下，直接对现实世界数据进行培训会产生对背景扰动的分类器。
We propose a novel setting for learning, where the input domain is the image of a map defined on the product of two sets, one of which completely determines the labels. We derive a new risk bound for this setting that decomposes into a bias and an error term, and exhibits a surprisingly weak dependence on the true labels. Inspired by these results, we present an algorithm aimed at minimizing the bias term by exploiting the ability to sample from each set independently. We apply our setting to visual classification tasks, where our approach enables us to train classifiers on datasets that consist entirely of a single synthetic example of each class. On several standard benchmarks for real-world image classification, we achieve robust performance in the context-agnostic setting, with good generalization to real world domains, whereas training directly on real world data without our techniques yields classifiers that are brittle to perturbations of the background.
