Stochastic-Shield

Qendro, Lorena; Ha, Sangwon; Jong, René de; Maji, Partha

doi:10.1145/3469261.3469404

Cited by 3 publications

(1 citation statement)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Bayesian deep learning approaches have been developed to address this challenge for domains where quantified uncertainty and the potential for introspection is expected [1]. Bayesian deep learning approaches for uncertainty quantification include Monte Carlo dropout [16,47], variational inference [9,31] and callibration [21]. The current study sets out to study a hybrid approach to enable uncertainty quantification by hybridizing deep neural networks with a nonparametric belief propagation algorithm.…”

Section: Diagnosability Adaptabilitymentioning

confidence: 99%

DNBP: Differentiable Nonparametric Belief Propagation

Opipari¹,

Pavlasek²,

Chen³

et al. 2023

Preprint

View full text Add to dashboard Cite

We present a differentiable approach to learn the probabilistic factors used for inference by a nonparametric belief propagation algorithm. Existing nonparametric belief propagation methods rely on domain-specific features encoded in the probabilistic factors of a graphical model. In this work, we replace each crafted factor with a differentiable neural network enabling the factors to be learned using an efficient optimization routine from labeled data. By combining differentiable neural networks with an efficient belief propagation algorithm, our method learns to maintain a set of marginal posterior samples using end-to-end training. We evaluate our differentiable nonparametric belief propagation (DNBP) method on a set of articulated pose tracking tasks and compare performance with learned baselines. Results from these experiments demonstrate the effectiveness of using learned factors for tracking and suggest the practical advantage over hand-crafted approaches. The project webpage is available at: https://progress.eecs.umich.edu/projects/dnbp/.

show abstract

Section: Diagnosability Adaptabilitymentioning

confidence: 99%

DNBP: Differentiable Nonparametric Belief Propagation

Opipari¹,

Pavlasek²,

Chen³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

When Monte-Carlo Dropout Meets Multi-Exit: Optimizing Bayesian Neural Networks on FPGA

Fan,

Chen,

Castelli

et al. 2023

2023 60th ACM/IEEE Design Automation Conference (DAC)

View full text Add to dashboard Cite

DNBP: Differentiable Nonparametric Belief Propagation

Opipari,

Pavlasek,

Chen

et al. 2024

ACM / IMS J. Data Sci.

View full text Add to dashboard Cite

We present a differentiable approach to learn the probabilistic factors used for inference by a nonparametric belief propagation algorithm. Existing nonparametric belief propagation methods rely on domain-specific features encoded in the probabilistic factors of a graphical model. In this work, we replace each crafted factor with a differentiable neural network, enabling the factors to be learned using an efficient optimization routine from labeled data. By combining differentiable neural networks with an efficient belief propagation algorithm, our method learns to maintain a set of marginal posterior samples using end-to-end training. We evaluate our differentiable nonparametric belief propagation (DNBP) method on a set of articulated pose tracking tasks and compare performance with learned baselines. Results from these experiments demonstrate the effectiveness of using learned factors for tracking and suggest the practical advantage over hand-crafted approaches. The project webpage is available at: https://progress.eecs.umich.edu/projects/dnbp/ .

show abstract

Stochastic-Shield

Cited by 3 publications

References 6 publications

DNBP: Differentiable Nonparametric Belief Propagation

DNBP: Differentiable Nonparametric Belief Propagation

When Monte-Carlo Dropout Meets Multi-Exit: Optimizing Bayesian Neural Networks on FPGA

DNBP: Differentiable Nonparametric Belief Propagation

Contact Info

Product

Resources

About