AI Paper Atlas

Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes

Vector Quantized Bayesian Neural Network Inference for Data Streams

Namuk Park, Taekyu Lee, Songkuk Kim

AAAI 2021 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Approximate inference in Bayesian neural networks · 8 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Replace repeated Bayesian forward passes with exponential temporal smoothing of recent predictionsBayesian U-Net · CamVid semantic segmentationstream throughput (Img/Sec): 0.788 -> 9.41Improved
Replace repeated Bayesian forward passes with exponential temporal smoothing of recent predictionsBayesian U-Net · NYUDv2 depth estimationstream throughput (Img/Sec): 1.61 -> 13.6Improved
Apply temporal smoothing to Bayesian predictionsBayesian U-Net · CamVid semantic segmentationNLL: 0.276 -> 0.253Improved
Apply temporal smoothing to Bayesian predictionsBayesian U-Net · NYUDv2 depth estimationRMSE (m): 0.705 -> 0.700Improved
Use deterministic weights instead of a Bayesian weight distribution while retaining temporal smoothing (ablation)VQ-BNN · CamVid semantic segmentationNLL: 0.253±0.009 -> 0.284±0.023Hurt
Reduce the number of recent prototypes (ablation)VQ-BNN · CamVid semantic segmentationNLLHurt
Increase the exponential-decay timescale up to 1.25 (ablation)VQ-BNN · CamVid semantic segmentationNLLImproved
Increase the exponential-decay timescale beyond 1.25 (ablation)VQ-BNN · CamVid semantic segmentationNLLHurt
Add future predictions to the temporal smoothing window (ablation)VQ-BNN · CamVid semantic segmentationNLLImproved
Reduce video frame rate and temporal consistency (ablation)VQ-BNN · CamVid semantic segmentationNLLHurt
Apply temporal smoothing to deterministic predictions rather than Bayesian predictions (ablation)DNN · CamVid semantic segmentationNLL: 0.314 -> 0.284Improved
Apply temporal smoothing to deterministic predictions rather than Bayesian predictions (ablation)DNN · NYUDv2 depth estimation, SegNetRMSE (m): 0.740±0.028 -> 0.717±0.042Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy