AI Paper Atlas

Research map / Label-efficient and robust learning / OOD and anomaly detection

Out-of-Distribution Detection for Monocular Depth Estimation

Julia Hornauer, Adrian Holzbock, Vasileios Belagiannis

ICCV 2023 · Label-efficient and robust learning › OOD and anomaly detection · approach: Spurious-aware OOD detection · 9 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
train encoder and decoder as autoencoder instead of reusing depth features (ablation)image decoder OOD detection (Monodepth2) · KITTI avg OODAUROC: 96.02 -> 52.17Hurt
train encoder and decoder as autoencoder instead of reusing depth features (ablation)image decoder OOD detection (MonoViT) · KITTI avg OODAUROC: 97.71 -> 35.04Hurt
train image decoder simultaneously with depth model instead of post hoc (ablation)image decoder (Monodepth2) · KITTI avg OODAUROC: 96.02 -> 98.57Improved
train image decoder simultaneously with depth model instead of post hoc (ablation)image decoder (MonoViT) · KITTI avg OODAUROC: 97.71 -> 94.20Hurt
train image decoder together with depth model (ablation)Monodepth2 · KITTIAbs Rel: 0.090 -> 0.101Hurt
train image decoder together with depth model (ablation)MonoViT · KITTIAbs Rel: 0.079 -> 0.085Hurt
reconstruction-error OOD score instead of PostMonodepth2 · KITTI vs vKITTIAUROC: 75.98 -> 99.40Improved
reconstruction-error OOD score instead of PostMonodepth2 · KITTI vs IndiaAUROC: 59.61 -> 89.29Improved
reconstruction-error OOD score instead of DropPixelformer · NYU vs PlacesAUROC: 88.13 -> 93.18Improved
reconstruction-error OOD score instead of LogMonodepth2 · NYU vs PlacesAUROC: 77.32 -> 74.84Hurt
reconstruction-error OOD score instead of LogMonodepth2 · NYU vs PlacesFPR95: 68.00 -> 65.33Improved
reconstruction-error OOD score instead of PostMonoViT · KITTI vs IndiaAUROC: 46.53 -> 95.95Improved

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