论文标题
以对象为中心的生成模型中的重建瓶颈
Reconstruction Bottlenecks in Object-Centric Generative Models
论文作者
论文摘要
存在一系列具有适当诱导偏见的方法，可以在没有监督的情况下学习图像的可解释的以对象为中心的表示。但是，这些在很大程度上仅限于视觉上简单的图像。现实世界中感觉数据集中的强大对象发现仍然难以捉摸。为了增加对这种归纳偏见的理解，我们从经验上研究了“重建瓶颈”对于现场分解在Genesis中的作用，Genesis是一个最近的基于VAE的模型。我们显示这样的瓶颈决定了重建和分割质量，并严重影响模型行为。
A range of methods with suitable inductive biases exist to learn interpretable object-centric representations of images without supervision. However, these are largely restricted to visually simple images; robust object discovery in real-world sensory datasets remains elusive. To increase the understanding of such inductive biases, we empirically investigate the role of "reconstruction bottlenecks" for scene decomposition in GENESIS, a recent VAE-based model. We show such bottlenecks determine reconstruction and segmentation quality and critically influence model behaviour.
