Multi-objects Generation with Amortized Structural Regularization

06/10/2019
by   Kun Xu, et al.
0

Deep generative models (DGMs) have shown promise in image generation. However, most of the existing work learn the model by simply optimizing a divergence between the marginal distributions of the model and the data, and often fail to capture the rich structures and relations in multi-object images. Human knowledge is a critical element to the success of DGMs to infer these structures. In this paper, we propose the amortized structural regularization (ASR) framework, which adopts the posterior regularization (PR) to embed human knowledge into DGMs via a set of structural constraints. We derive a lower bound of the regularized log-likelihood, which can be jointly optimized with respect to the generative model and recognition model efficiently. Empirical results show that ASR significantly outperforms the DGM baselines in terms of inference accuracy and sample quality.

READ FULL TEXT

page 1

page 3

page 7

page 8

page 11

page 12

research
06/26/2018

Deep Generative Models with Learnable Knowledge Constraints

The broad set of deep generative models (DGMs) has achieved remarkable a...
research
06/13/2019

Reweighted Expectation Maximization

Training deep generative models with maximum likelihood remains a challe...
research
06/12/2015

Bidirectional Helmholtz Machines

Efficient unsupervised training and inference in deep generative models ...
research
07/11/2018

VFunc: a Deep Generative Model for Functions

We introduce a deep generative model for functions. Our model provides a...
research
04/03/2017

Semi-Supervised Generation with Cluster-aware Generative Models

Deep generative models trained with large amounts of unlabelled data hav...
research
03/20/2016

Joint Stochastic Approximation learning of Helmholtz Machines

Though with progress, model learning and performing posterior inference ...
research
09/23/2015

Deep Temporal Sigmoid Belief Networks for Sequence Modeling

Deep dynamic generative models are developed to learn sequential depende...

Please sign up or login with your details

Forgot password? Click here to reset