AI Paper Atlas

Research map / 3D vision / Depth and stereo

Multi-Loss Rebalancing Algorithm for Monocular Depth Estimation

Jae-Han Lee, Chang-Su Kim

ECCV 2020 · 3D vision › Depth and stereo · approach: Self-supervised monocular depth · 51 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 weight rebalancing (lambda 3 to -3) with initialization to all 78 losses (ablation)loss rebalancing depth estimator · NYUv2delta1: 86.4% -> 87.0%Improved
add weight rebalancing (lambda 3 to -3) with initialization to all 78 losses (ablation)loss rebalancing depth estimator · NYUv2RMSElin: 0.440 -> 0.434Improved
add weight initialization before rebalancing (ablation)loss rebalancing depth estimator · NYUv2delta1: 85.6% -> 87.0%Improved
add weight initialization alone, without rebalancing (ablation)loss rebalancing depth estimator · NYUv2delta1: 86.4% -> 86.5%No clear effect
use rebalancing on finest-scale losses only (L0) (ablation)loss rebalancing depth estimator · NYUv2delta1: 85.3% -> 84.8%Hurt
add rebalancing to coarse-scale losses L3 U L4 U L5 (ablation)loss rebalancing depth estimator · NYUv2delta1: 86.6% -> 86.7%Improved
use decreasing lambda 3 to -3 instead of constant lambda -3 (ablation)loss rebalancing depth estimator · NYUv2delta1: 84.7% -> 87.0%Improved
use decreasing lambda 3 to -3 instead of constant lambda 3 (ablation)loss rebalancing depth estimator · NYUv2delta1: 86.6% -> 87.0%Improved
widen lambda schedule to 5 to -5 instead of 3 to -3 (ablation)loss rebalancing depth estimator · NYUv2delta1: 87.0% -> 86.4%Hurt
replace uncertainty weighting [21] with proposed rebalancing (ablation)loss rebalancing depth estimator · NYUv2delta1: 85.6% -> 87.0%Improved
use all 78 losses instead of the single depth loss (ablation)loss rebalancing depth estimator · NYUv2delta1: 84.8% -> 86.4%Improved
add gradient losses to depth losses (multi-scale) (ablation)loss rebalancing depth estimator · NYUv2delta1: 84.8% -> 86.5%Improved

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