AI Paper Atlas

Research map / Label-efficient and robust learning / Test-time adaptation

PointFix: Learning to Fix Domain Bias for Robust Online Stereo Adaptation

Kwonyoung Kim, Jungin Park, Jiyoung Lee, Dongbo Min, Kwanghoon Sohn

ECCV 2022 · Label-efficient and robust learning › Test-time adaptation · approach: Test-time adaptation of vision-language models · 5 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 meta-learning (ML) to training the base network (ablation)MADNet with full adaptation · KITTI short-termD1-all: 6.68 -> 3.12Improved
add PointFixNet point loss without meta-learning (ablation)MADNet with full adaptation · KITTI short-termD1-all: 6.68 -> 8.06Hurt
add PointFixNet on top of meta-learning (ablation)MADNet with full adaptation · KITTI short-termD1-all: 3.12 -> 2.00Improved
add PointFixNet on top of meta-learning (ablation)MADNet with full adaptation · KITTI short-termEPE: 0.96 -> 0.74Improved
train MADNet with PointFix before adaptationMADNet · KITTI mid-term, no adaptationD1-all: 38.35 -> 16.94Improved
train MADNet with PointFix before adaptationMADNet · KITTI mid-term, no adaptationEPE: 8.18 -> 2.12Improved
train MADNet with PointFix, full adaptationMADNet · KITTI short-termD1-all: 6.68 -> 2.00Improved
train MADNet with PointFix, MAD adaptationMADNet · KITTI short-termD1-all: 11.82 -> 2.64Improved
train MADNet with PointFix, MAD adaptationMADNet · KITTI mid-termD1-all: 4.15 -> 2.16Improved
use PointFix with MAD adaptation instead of MADNet with MAD++ adaptationMADNet · KITTI mid-termD1-all: 3.56 -> 2.16Improved
train MADNet with PointFix, no adaptationMADNet · DrivingStereo weather, short-termD1-all: 58.12 -> 33.52Improved
train MADNet with PointFix, MAD adaptationMADNet · DrivingStereo weather, short-termD1-all: 30.11 -> 9.48Improved

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