AI Paper Atlas

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

Efficient Uncertainty Estimation for Semantic Segmentation in Videos

Po-Yu Huang, Wan-Ting Hsu, Chun-Yueh Chiu, Ting-Fan Wu, Min Sun

ECCV 2018 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Priors and functional variational uncertainty · 128 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 N=50 MC dropout sampling with temporal aggregation (TA-MC)SegNet · CamVidmean IoU: 63.7 -> 62.1Hurt
replace N=50 MC dropout sampling with temporal aggregation (TA-MC)Tiramisu · CamVidinference time (s): 11.72 -> 0.37Improved
reduce MC dropout samples from 50 to 5Tiramisu MC · CamVidmean IoU: 64.0 -> 62.4Hurt
add region-based multiplying factor (RTA) to TA-MC (ablation)SegNet · CamVidmean IoU: 62.1 -> 62.5Improved
add region-based multiplying factor (RTA) to TA-MC (ablation)Tiramisu · CamVidmean IoU: 62.3 -> 62.4No clear effect
add region-based multiplying factor (RTA) to TA-MC (ablation)SegNet · CamVidKendall tau (Entropy): 0.626 -> 0.662Improved
add region-based multiplying factor (RTA) to TA-MC (ablation)SegNet · CamVidKendall tau (Variation Ratio): 0.631 -> 0.674Improved
add region-based multiplying factor (RTA) to TA-MC (ablation)SegNet · CamVidKendall tau (Mean STD): 0.540 -> 0.627Improved
add region-based multiplying factor (RTA) to TA-MC (ablation)Tiramisu · CamVidKendall tau (Entropy): 0.660 -> 0.664No clear effect
add region-based multiplying factor (RTA) to TA-MC (ablation)Tiramisu · CamVidKendall tau (BALD): 0.626 -> 0.612Hurt
add region-based multiplying factor (RTA) to TA-MC (ablation)SegNet · CamVidRanking IoU 30% (Variation Ratio): 63.8 -> 65.2Improved
use RTA-MC instead of MC dropout for uncertainty rankingSegNet · CamVidKendall tau (Entropy): 0.647 -> 0.662Improved

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