Reconstruction Bottlenecks in Object-Centric Generative Models
arXiv:2007.06245
Abstract
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.
arXiv comment10 pages, 7 Figures, Workshop on Object-Oriented Learning at ICML 2020
References in corpus (17)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Auto-Encoding Variational Bayes
- Opening the Black Box of Deep Neural Networks via Information
- Multi-Object Representation Learning with Iterative Variational Inference
- MONet: Unsupervised Scene Decomposition and Representation
- GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations
- Relational Neural Expectation Maximization: Unsupervised Discovery of Objects and their Interactions
- BlockGAN: Learning 3D Object-aware Scene Representations from Unlabelled Images
- Sequential Attend, Infer, Repeat: Generative Modelling of Moving Objects
- Spatial Broadcast Decoder: A Simple Architecture for Learning Disentangled Representations in VAEs
- COBRA: Data-Efficient Model-Based RL through Unsupervised Object Discovery and Curiosity-Driven Exploration
- Unsupervised Object Segmentation by Redrawing
- Object Discovery with a Copy-Pasting GAN
- Efficient inference in occlusion-aware generative models of images
- SCALOR: Generative World Models with Scalable Object Representations
- Towards causal generative scene models via competition of experts
- Emergence of Object Segmentation in Perturbed Generative Models