paper-with-me

Papers

Table-Top Scene Analysis Using Knowledge-Supervised MCMC

2020-02-19 · Ziyuan Liu, Dong Chen, Kai M. Wurm, Georg von Wichert

In this paper, we propose a probabilistic method to generate abstract scene graphs for table-top scenes from 6D object pose estimates. We explicitly make use of task-specfic context knowledge by encoding this knowledge as descriptive rules in Markov logic networks. Our approach to generate scene graphs is probabilistic: Uncertainty in the object poses is addressed by a probabilistic sensor model that is embedded in a data driven MCMC process. We apply Markov logic inference to reason about hidden objects and to detect false estimates of object poses. The effectiveness of our approach is demonstrated and evaluated in real world experiments.

📄 PDF Abstract BibTeX arXiv:2002.08417

Code (0)

등록된 구현이 없습니다.

Tasks

DescriptiveObject

Similar Papers 제목 키워드 기반

Knowledge Removal in Sampling-based Bayesian Inference

2022-03-24 · ICLR 2022 4 · Shaopeng Fu, Fengxiang He, DaCheng Tao

The right to be forgotten has been legislated in many countries, but its enforcement in the AI industry would cause unbearable costs. When single data deletion requests come, companies may need to delete the whole models…

Bayesian InferenceMachine Unlearning

On the Anatomy of MCMC-Based Maximum Likelihood Learning of Energy-Based Models

2019-03-29 · Erik Nijkamp, Mitch Hill, Tian Han, Song-Chun Zhu 외

This study investigates the effects of Markov chain Monte Carlo (MCMC) sampling in unsupervised Maximum Likelihood (ML) learning. Our attention is restricted to the family of unnormalized probability densities for which …

Anatomy

Learning Energy-Based Model with Variational Auto-Encoder as Amortized Sampler

2020-12-29 · Jianwen Xie, Zilong Zheng, Ping Li

Due to the intractable partition function, training energy-based models (EBMs) by maximum likelihood requires Markov chain Monte Carlo (MCMC) sampling to approximate the gradient of the Kullback-Leibler divergence betwee…

Non-convex Learning via Replica Exchange Stochastic Gradient MCMC

2020-08-12 · ICML 2020 1 · Wei Deng, Qi Feng, Liyao Gao, Faming Liang 외

Replica exchange Monte Carlo (reMC), also known as parallel tempering, is an important technique for accelerating the convergence of the conventional Markov Chain Monte Carlo (MCMC) algorithms. However, such a method req…

Image Classification

Generative VoxelNet: Learning Energy-Based Models for 3D Shape Synthesis and Analysis

2020-12-25 · Jianwen Xie, Zilong Zheng, Ruiqi Gao, Wenguan Wang 외

3D data that contains rich geometry information of objects and scenes is valuable for understanding 3D physical world. With the recent emergence of large-scale 3D datasets, it becomes increasingly crucial to have a power…

3D Object ClassificationSuper-Resolution