AI Paper Atlas

Research map / Detection and segmentation / CNN features

Mitigating Intensity Bias in Shadow Detection via Feature Decomposition and Reweighting

Lei Zhu, Ke Xu, Zhanghan Ke, Rynson W.H. Lau

ICCV 2021 · Detection and segmentation › CNN features · approach: RGB-D salient object detection · 69 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 the intensity-invariant consistency loss Li (ablation)Basic+BB · SBUBER: 3.32 -> 3.24Improved
add the intensity-variant prediction loss Lv alone (ablation)Basic+BB · SBUBER: 3.32 -> 3.36Hurt
add Lv to Basic+BB+Li (paired self-supervision) (ablation)Basic+BB+Li · SBUBER: 3.24 -> 3.04Improved
add bilateral branches without decomposition losses (ablation)Basic · SBUBER: 3.32 -> 3.32No clear effect
use ill-posed Lv (no reference image) instead of well-posed Lv (ablation)FDRNet · SBUBER: 3.21 -> 3.04Improved
replace constant mu=0.5 with parabolic decay cumulative learning (ablation)FDRNet · SBUBER: 3.45 -> 3.04Improved
replace learnable mu (backward) with parabolic decay (ablation)FDRNet · SBUBER: 3.47 -> 3.04Improved
replace mu predicted by extra branch (forward) with parabolic decay (ablation)FDRNet · SBUBER: 3.42 -> 3.04Improved
use decay instead of increment of mu (ablation)FDRNet · SBUBER: 3.63 -> 3.26Improved
use parabolic decay instead of linear decay of mu (ablation)FDRNet · SBUBER: 3.26 -> 3.04Improved
set test-time mu to extreme values 0 or 1 instead of 0.4 (ablation)FDRNet · SBUBERHurt
random brightness shift data augmentation (ablation)FPN-like network · SBUBERHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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