AI Paper Atlas

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

Uncertainty Quantification in Depth Estimation via Constrained Ordinal Regression

Dongting Hu, Liuhua Peng, Tingjin Chu, Xiaoxing Zhang, Yinian Mao, Howard Bondell, Mingming Gong

ECCV 2022 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Priors and functional variational uncertainty · 12 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
add estimation variance to error variance (predictive variance) (ablation)ConOR+WBS · KITTI (Eigen split)AUSE (rmse): 0.097 -> 0.095Improved
add estimation variance to error variance (predictive variance) (ablation)ConOR+WBS · NYUv2AUSE (rmse): 0.305 -> 0.297Improved
use constrained ordinal regression instead of unconstrained OR (ablation)ConOR · KITTI (Eigen split)AUSE (rmse): 0.108 -> 0.097Improved
use constrained ordinal regression instead of unconstrained OR (ablation)ConOR · KITTI (Eigen split)depth rmse: 2.766 -> 2.709Improved
use constrained ordinal regression instead of unconstrained OR (ablation)ConOR · NYUv2AUSE (rmse): 0.314 -> 0.305Improved
add MC dropout for estimation variance (ablation)ConOR · KITTI (Eigen split)AUSE (rmse): 0.097 -> 0.104Hurt
add deep ensemble for estimation variance (ablation)ConOR · KITTI (Eigen split)AUSE (rmse): 0.097 -> 0.096No clear effect
add multiplier bootstrap for estimation variance (ablation)ConOR · KITTI (Eigen split)AUSE (rmse): 0.097 -> 0.094Improved
add wild bootstrap for estimation variance (ablation)ConOR · NYUv2AUSE (rmse): 0.305 -> 0.297Improved
add MC dropout for estimation variance (ablation)ConOR · NYUv2AUSE (rmse): 0.305 -> 0.305No clear effect
use spacing-increasing discretization instead of uniform (ablation)ConOR · KITTI (Eigen split)rmse and uncertaintyImproved
increase number of bins (ablation)ConOR · KITTI (Eigen split)uncertainty estimation: rmse stays between 2.7 and 2.8Improved

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