论文标题
利用2D转换的系统知识
Leveraging Systematic Knowledge of 2D Transformations
论文作者
论文摘要
现有的深度学习模型遭受了计算机视觉任务的分布（O.O.D.）的性能下降。相比之下，人类具有出色的解释图像的能力，即使图像中的场景很少见，这要归功于获得的知识的系统性。这项工作的重点是1）获得2D转换的系统知识，以及2）可以利用O.O.D.图像分类任务中学习知识的架构组件。环境。通过基于因果框架下构建的合成数据集的新培训方法，深度神经网络从语义上不同的域（例如，甚至是从噪声中）获取知识，并且在参数估计实验中表现出一定水平的系统性。基于此，设计了一种新颖的体系结构，该体系结构由分类器，估计器和标识符组成（缩写为“ CED”）。通过模拟人类视觉感知中的“假设验证”过程，CED可以在协变性转移下显着提高分类精度。
The existing deep learning models suffer from out-of-distribution (o.o.d.) performance drop in computer vision tasks. In comparison, humans have a remarkable ability to interpret images, even if the scenes in the images are rare, thanks to the systematicity of acquired knowledge. This work focuses on 1) the acquisition of systematic knowledge of 2D transformations, and 2) architectural components that can leverage the learned knowledge in image classification tasks in an o.o.d. setting. With a new training methodology based on synthetic datasets that are constructed under the causal framework, the deep neural networks acquire knowledge from semantically different domains (e.g. even from noise), and exhibit certain level of systematicity in parameter estimation experiments. Based on this, a novel architecture is devised consisting of a classifier, an estimator and an identifier (abbreviated as "CED"). By emulating the "hypothesis-verification" process in human visual perception, CED improves the classification accuracy significantly on test sets under covariate shift.
