AI Paper Atlas

Research map / 3D vision / Depth and stereo

Prior Guided Dropout for Robust Visual Localization in Dynamic Environments

Zhaoyang Huang, Yan Xu, Jianping Shi, Xiaowei Zhou, Hujun Bao, Guofeng Zhang

ICCV 2019 · 3D vision › Depth and stereo · approach: Scene coordinate regression for localization · 53 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 prior guided dropout (ablation)MapNet · RobotCar Fullposition error (m): 44.61 -> 32.64Improved
add composite self-attention (ablation)MapNet · RobotCar Fullposition error (m): 44.61 -> 30.02Improved
add composite self-attention (ablation)PoseNet · RobotCar Fullposition error (m): 46.61 -> 62.46Hurt
add composite self-attention on top of prior guided dropout (ablation)PoseNet · RobotCar Fullposition error (m): 38.56 -> 33.82Improved
add composite self-attention on top of prior guided dropout (ablation)MapNet · RobotCar Fullposition error (m): 32.64 -> 19.18Improved
use variational PGO instead of constant PGO (ablation)AD-MapNet · RobotCar Fullposition error (m): 18.84 -> 14.85Improved
add constant PGOAD-MapNet · RobotCar Fullorientation error (deg): 4.60 -> 13.73Hurt
use variational PGO instead of constant PGO (ablation)AD-PoseNet · RobotCar Loopposition error (m): 7.04 -> 6.49Improved
add constant PGOAD-PoseNet · RobotCar Fullposition error (m): 33.82 -> 27.35Improved
use prior guided dropout instead of uniform dropout (T=0.2) (ablation)AD-MapNet · RobotCar Fullposition error (m): 53.69 -> 19.18Improved
set dropout threshold T=0.2 instead of 0.4 (ablation)AD-MapNet · RobotCar Fullposition error (m): 33.03 -> 19.18Improved
set dropout threshold T=0.2 instead of 0.1 (ablation)AD-MapNet · RobotCar Loopposition error (m): 5.65 -> 6.45Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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