论文标题
通过神经网络训练的结构化（DE）组合表示
Structured (De)composable Representations Trained with Neural Networks
论文作者
论文摘要
本文提出了一种新颖的技术，用于代表概念类的模板和实例。模板表示是指捕获整个类的特征的通用表示。提出的技术使用端到端的深度学习从输入图像和离散标签中学习结构化和可组合的表示。获得的表示形式基于类标签给出的分布与通过上下文信息给出的分布之间的距离估计，这些分布被建模为环境。我们证明表示形式具有清晰的结构，可以将表示形式分解为代表类和环境的因素。我们评估了有关涉及不同方式（视觉和语言数据）的分类和检索任务的新技术。
The paper proposes a novel technique for representing templates and instances of concept classes. A template representation refers to the generic representation that captures the characteristics of an entire class. The proposed technique uses end-to-end deep learning to learn structured and composable representations from input images and discrete labels. The obtained representations are based on distance estimates between the distributions given by the class label and those given by contextual information, which are modeled as environments. We prove that the representations have a clear structure allowing to decompose the representation into factors that represent classes and environments. We evaluate our novel technique on classification and retrieval tasks involving different modalities (visual and language data).
