LAVAE: Disentangling Location and AppearanceDownload PDF

25 Sep 2019 (modified: 24 Dec 2019)ICLR 2020 Conference Blind SubmissionReaders: Everyone
  • Original Pdf: pdf
  • Keywords: structured scene representations, compositional representations, generative models, unsupervised learning
  • TL;DR: Generative model that learns structured, interpretable, object-based representations of visual scenes, disentangling object location and appearance.
  • Abstract: We propose a probabilistic generative model for unsupervised learning of structured, interpretable, object-based representations of visual scenes. We use amortized variational inference to train the generative model end-to-end. The learned representations of object location and appearance are fully disentangled, and objects are represented independently of each other in the latent space. Unlike previous approaches that disentangle location and appearance, ours generalizes seamlessly to scenes with many more objects than encountered in the training regime. We evaluate the proposed model on multi-MNIST and multi-dSprites data sets.
6 Replies