AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Mapillary Planet-Scale Depth Dataset

Manuel López Antequera, Pau Gargallo, Markus Hofinger, Samuel Rota Bulò, Yubin Kuang, Peter Kontschieder

ECCV 2020 · Architectures and efficiency › Pruning and efficient tuning · approach: Efficient ViT adaptation

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
train on MPSD instead of MegaDepth (camera normalization)u-net depth network · KITTISILog: 26.79 -> 12.77Improved
train on MPSD instead of MegaDepth (camera normalization)u-net depth network · CityscapesSILog: 36.73 -> 19.77Improved
train on MPSD instead of MegaDepth (camera normalization)u-net depth network · Make3DSILog: 41.64 -> 27.49Improved
train on MPSD instead of MegaDepth (camera normalization)u-net depth network · MegaDepthSILog: 9.96 -> 14.68Hurt
use full MPSD rather than size-matched mini MPSD (ablation)u-net depth network · KITTISILog: 14.89 -> 12.77Improved
add camera normalization instead of naive resize when training on MegaDepth (ablation)MegaDepth u-net · CityscapesSILog: 65.11 -> 36.73Improved
use CAM-Convs instead of camera normalization on MPSDMPSD u-net · CityscapesSILog: 19.77 -> 34.83Hurt
use random instead of center crops with CAM-Convs on MegaDepth (ablation)CAM-Convs MegaDepth · KITTISILog: 23.79 -> 26.92No clear effect
combine camera normalization with CAM-Convs on MPSD (ablation)MPSD camera normalization · DIODESILog: 42.2 -> 41.69Improved
fine-tune MPSD network on KITTIMPSD camera normalization · KITTISILog: 12.77 -> 9.23Improved
fine-tune MPSD network on KITTIMPSD camera normalization · CityscapesSILog: 19.77 -> 27.11Hurt
pre-train on MPSD instead of MegaDepth before KITTI fine-tuningdepth network · KITTI val dynamic regionsRMSE (m): 4.29 -> 3.52Improved

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