想象看不见的东西:在具有密集潜在树的不完整图像上学习分布
Imagining the Unseen: Learning a Distribution over Incomplete Images with Dense Latent Trees
摘要:
图像被组成为对象部分的层次结构。我们使用这种洞察力来创建一个生成图形模型,该模型定义了图像部分的分层分布。通常,由于图中的循环,这会导致难以处理的推理。我们提出了一种替代的模型结构,密集的潜在树(DLT),它避免了循环,并允许高效的精确推理,同时保持层次结构的部分之间的密集连接。DLT的有用性示出了部分观察到的MNIST和时尚MNIST数据的图像完成的示例任务。我们通过可视化其潜在状态来验证是否成功地学习了图像的分层模型。
英文摘要:
Images are composed as a hierarchy of object parts. We use this insight to create a generative graphical model that defines a hierarchical distribution over image parts. Typically, this leads to intractable inference due to loops in the graph. We propose an alternative model structure, the Dense Latent Tree (DLT), which avoids loops and allows for efficient exact inference, while maintaining a dense connectivity between parts of the hierarchy. The usefulness of DLTs is shown for the example task of image completion on partially observed MNIST and Fashion-MNIST data. We verify having successfully learned a hierarchical model of images by visualising its latent states.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。