AI Paper Atlas

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

RoboDepth: Robust Out-of-Distribution Depth Estimation under Corruptions

Lingdong Kong, Shaoyuan Xie, Hanjiang Hu, Lai Xing Ng, Benoit R Cottereau, Wei Tsang Ooi

NeurIPS 2023 · Label-efficient and robust learning › OOD and anomaly detection · approach: Spurious-aware OOD detection · 11 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
Use a Transformer-based MDE model rather than a conventional CNNMDE models · KITTI-CmCE: 100.00 -> 74.95Improved
Train using monocular images rather than stereo or mixed monocular and stereo inputs (ablation)MonoDepth2 · KITTI-CmCE: 100.00 -> 124.31Improved
Add ImageNet pre-training (ablation)MonoDepth2 · KITTI-Crobustness to weather, lighting, and data-processing corruptionsMixed
Train with higher-resolution inputs (ablation)MDE models · KITTI-C noise corruptionsrobustness: 30%Improved
Increase the number of trainable parametersMDE models · corruption robustnessrobustnessHurt
Increase training complexityMDE models · corruption robustnessrobustnessImproved
Fine-tune on the same corruption used for evaluation (ablation)MonoDepth2 · KITTI-Crobustness to that corruptionImproved
Fine-tune using severe weather or movement corruptions (ablation)MonoDepth2 · KITTI-Coverall robustnessHurt
Apply simulated corruption fine-tuning (ablation)MonoDepth2 · nuScenes and Foggy-Cityscapesdistribution gapImproved
Evaluate on stylized images with texture cues diminishedMDE models · KITTI-SmDEEHurt
Use a model with global awarenessMDE models · KITTI-SmDEEImproved

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