Deep Part-Based Generative Shape Model with Latent Variables
نویسندگان
چکیده
The Shape Boltzmann Machine (SBM) [6] and its multilabel version MSBM [5] have been recently introduced as deep generative models that capture the variations of an object shape. While being more flexible MSBM requires datasets with labeled parts of the objects for training. In the paper we present an algorithm for training MSBM using binary masks of objects and the seeds which approximately correspond to the locations of objects parts. The latter can be obtained from part-based detectors in an unsupervised manner. We derive a latent variable model and an EM-like training procedure for adjusting the weights of MSBM using a deep learning framework. We show that the model trained by our method outperforms SBM in the tasks related to binary shapes and is very close to the original MSBM in terms of quality of multilabel shapes.
منابع مشابه
Learning Deep Generative Models with Discrete Latent Variables
There have been numerous recent advancements on learning deep generative models with latent variables thanks to the reparameterization trick that allows to train deep directed models effectively. However, since reparameterization trick only works on continuous variables, deep generative models with discrete latent variables still remain hard to train and perform considerably worse than their co...
متن کاملLearning Deep Generative Models With Discrete Latent Variables
There have been numerous recent advancements on learning deep generative models with latent variables thanks to the reparameterization trick that allows to train deep directed models effectively. However, since reparameterization trick only works on continuous variables, deep generative models with discrete latent variables still remain hard to train and perform considerably worse than their co...
متن کاملDeep Recurrent Generative Decoder for Abstractive Text Summarization
We propose a new framework for abstractive text summarization based on a sequence-to-sequence oriented encoderdecoder model equipped with a deep recurrent generative decoder (DRGN). Latent structure information implied in the target summaries is learned based on a recurrent latent random model for improving the summarization quality. Neural variational inference is employed to address the intra...
متن کاملReweighted Wake-Sleep
Training deep directed graphical models with many hidden variables and performing inference remains a major challenge. Helmholtz machines and deep belief networks are such models, and the wake-sleep algorithm has been proposed to train them. The wake-sleep algorithm relies on training not just the directed generative model but also a conditional generative model (the inference network) that run...
متن کاملExplaining monkey face patch system as deep inverse graphics
1. Summary The spiking patterns of the neurons at different fMRI-identified face patches show a hierarchical organization of selectivity for faces: neurons at the most posterior patch (ML/MF) appear to be tuned to specific view points, AL (a more anterior patch) neurons exhibit specificity to mirror-symmetric view points, and the most anterior patch (AM) appear to be largely viewinvariant, i.e....
متن کامل