AI Paper Atlas

Research map / Label-efficient and robust learning / Knowledge distillation

Monitored Distillation for Positive Congruent Depth Completion

Tian Yu Liu, Parth Agrawal, Allison Chen, Byung-Woo Hong, Alex Wong

ECCV 2022 · Label-efficient and robust learning › Knowledge distillation · approach: Few-shot and metric distillation · 38 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 sparse depth error weight beta to teacher selection (ablation)Monitored Distillation · VOID (supervised ensemble)MAE: 32.86 -> 30.88Improved
add sparse depth error weight beta to teacher selection (ablation)Monitored Distillation · VOID (unsupervised ensemble)MAE: 38.78 -> 36.42Improved
add sparse depth error weight beta to teacher selection (ablation)Monitored Distillation · VOID (heterogeneous ensemble)MAE: 32.09 -> 29.67Improved
add unsupervised loss to mean distillation (ablation)Mean ensemble distillation · VOID (heterogeneous ensemble)MAE: 44.53 -> 35.79Improved
add unsupervised loss to mean distillation (ablation)Mean ensemble distillation · VOID (supervised ensemble)MAE: 34.27 -> 34.04No clear effect
replace mean ensembling with monitored distillationMean ensemble distillation · VOID (heterogeneous ensemble)MAE: 35.79 -> 29.67Improved
add weaker teachers to a naive mean ensemble (supervised to heterogeneous)Mean ensemble distillation · VOIDMAE: 34.04 -> 35.79Hurt
add ScaffNet to the FusionNet and KBNet ensemble (ablation)Monitored Distillation · VOIDMAE: 40.10 -> 36.42Improved
train teachers on NYUv2 and SceneNet instead of VOID (ablation)Monitored Distillation · VOIDMAE: 36.42 -> 46.66Hurt
distill from monitored blind ensemble instead of single best teacher NLSPNDistill NLSPN · KITTI validationMAE: 221.077 -> 218.222Improved
distill from single teacher instead of mean of ensemble (ablation)Mean ensemble distillation · KITTI validationMAE: 232.481 -> 221.077Improved
reduce sparse depth density from 0.50% to 0.05%Monitored Distillation · VOIDMAE: 29.666 -> 104.966Hurt

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