AI Paper Atlas

Research map / Detection and segmentation / CNN features

Joint Learning of Intrinsic Images and Semantic Segmentation

Anil S. Baslamisli, Thomas T. Groenestege, Partha Das, Hoang-An Le, Sezer Karaoglu, Theo Gevers

ECCV 2018 · Detection and segmentation › CNN features · approach: Context modeling for semantic segmentation · 62 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 ground-truth albedo instead of RGB as SegNet input (ablation)SegNet · NED test (synthetic, 16 classes)mIoU: 0.5217 -> 0.5810Improved
use RGB plus albedo input instead of RGB only (ablation)SegNet · NED test (synthetic, 16 classes)mIoU: 0.5217 -> 0.5577Improved
add albedo to RGB input versus albedo alone (ablation)SegNet · NED test (synthetic, 16 classes)mIoU: 0.5810 -> 0.5577Hurt
add ground-truth segmentation labels as input to intrinsic decomposition (ablation)ShapeNet · NED test (synthetic, 16 classes)albedo MSE: 0.0094 -> 0.0076Improved
add ground-truth segmentation labels as input (ablation)ShapeNet · NED test (synthetic, 16 classes)shading DSSIM: 0.1303 -> 0.1312No clear effect
jointly learn intrinsics with segmentation instead of SegNetsegmentation network · NED test (synthetic, 16 classes)mIoU: 0.5217 -> 0.6332Improved
jointly learn segmentation with intrinsicsShapeNet · NED test (synthetic, 16 classes)albedo MSE: 0.0094 -> 0.0030Improved
joint network instead of single-task cascadesegmentation · NED test (synthetic, 16 classes)mIoU: 0.5810 -> 0.6332Improved
raise intrinsic loss weight w from 1 to 2 (ablation)Joint model · NED test (synthetic, 16 classes)mIoU: 0.533 -> 0.633Improved
raise intrinsic loss weight w from 2 to 4 (ablation)Joint model · NED test (synthetic, 16 classes)mIoU: 0.633 -> 0.611Hurt
set intrinsic loss weight w to 0.5 instead of 2 (ablation)Joint model · NED test (synthetic, 16 classes)global pixel accuracy: 0.9302 -> 0.7038Hurt
raise gamma_SMSE from 0.95 to 0.99 (ablation)ShapeNet intrinsic loss · NED test (synthetic, 16 classes)MSE: 0.0083 -> 0.0043Improved

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