AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Domain-invariant Stereo Matching Networks

Feihu Zhang, Xiaojuan Qi, Ruigang Yang, Victor Prisacariu, Benjamin Wah, Philip Torr

ECCV 2020 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Augmentation and mixture-of-experts generalization

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 batch norm with domain normalization (ablation)DSMNet · SceneFlow-trained, tested on KITTI2-pixel error (%): 9.4 -> 7.9Improved
replace batch norm with domain normalization (ablation)DSMNet · SceneFlow-trained, tested on Middlebury3-pixel error (%): 30.3 -> 27.1Improved
add 3 non-local filter layers to features (ablation)DSMNet with DN · SceneFlow-trained, tested on Middlebury3-pixel error (%): 27.1 -> 24.2Improved
increase feature non-local filter layers from 3 to 7 (ablation)DSMNet with DN · SceneFlow-trained, tested on Middlebury3-pixel error (%): 24.2 -> 22.9Improved
increase feature non-local filter layers from 7 to 9 (ablation)DSMNet with DN · SceneFlow-trained, tested on KITTI2-pixel error (%): 6.8 -> 6.8No clear effect
add 2 cost-volume non-local filter layers (ablation)DSMNet with DN + 7 NLF · SceneFlow-trained, tested on Middlebury3-pixel error (%): 22.9 -> 21.8Improved
add domain normalization and non-local filters to PSMNetPSMNet · SceneFlow-trained, tested on KITTI2-pixel error (%): 16.3 -> 8.5Improved
add domain normalization and non-local filters to GANetGANet · SceneFlow-trained, tested on Middlebury3-pixel error (%): 32.2 -> 23.7Improved
use domain normalization instead of instance norm (ablation)DSMNet · SceneFlow-trained, tested on KITTIerror rate (%): 6.4 -> 4.1Improved
use graph-based non-local filter instead of affinity propagation (ablation)DSMNet · Middlebury fullerror rate (%): 23.1 -> 20.1Improved
add non-local filtering layers to GANet-deep before KITTI fine-tuningGANet-deep · KITTI 2015 benchmark (fine-tuned)error rate (%), all area: 1.81 -> 1.77Improved
add Carla synthetic stereo data to SceneFlow trainingDSMNet · KITTI 2012error rate (%): 6.2 -> 3.9Improved

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