用符号语言让神经网络自动拆解图像中的物体与变换关系。
Disentangling Visual Priors: Unsupervised Learning of Scene Interpretations with Compositional Autoencoder
- 用领域语言定义图像生成的先验，如形状、外观、几何变换。
- 从少量图像中学习参数，实现对噪声和新场景的鲁棒推断。
- 适合研究可解释视觉模型或小样本学习的研究者。
当前深度学习模型缺乏系统捕捉和处理基本视觉概念（如物体、形状、几何变换等）的方法。本文提出一种神经符号架构，利用领域特定语言编码图像生成的先验知识，包括物体形状、外观、分类及几何变换。通过卷积神经网络从场景中提取特征，参数化模板程序并执行生成几何原型，再通过渲染与场景内容对比，以梯度反向传播进行自关联训练。在合成基准上的实验表明，该方法能有效解耦图像生成过程中的关键因素，仅需少量数据即可学习，在噪声干扰下保持正确推理，并具备良好的泛化能力。
原文摘要 · Abstract (English)
Contemporary deep learning architectures lack principled means for capturing and handling fundamental visual concepts, like objects, shapes, geometric transforms, and other higher-level structures. We propose a neurosymbolic architecture that uses a domain-specific language to capture selected priors of image formation, including object shape, appearance, categorization, and geometric transforms. We express template programs in that language and learn their parameterization with features extracted from the scene by a convolutional neural network. When executed, the parameterized program produces geometric primitives which are rendered and assessed for correspondence with the scene content and trained via auto-association with gradient. We confront our approach with a baseline method on a synthetic benchmark and demonstrate its capacity to disentangle selected aspects of the image formation process, learn from small data, correct inference in the presence of noise, and out-of-sample generalization.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。