AI Paper Atlas

Research map / Detection and segmentation / Weakly supervised detection and segmentation

What Synthesis Is Missing: Depth Adaptation Integrated With Weak Supervision for Indoor Scene Parsing

Keng-Chi Liu, Yi-Ting Shen, Jan P. Klopp, Liang-Gee Chen

ICCV 2019 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised object localization · 7 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 min-max normalization to the depth adversarial loss (ablation)depth adaptation · SUN RGB-D val (raw depth)mIoU (w/o windows): 26.44 -> 30.95Improved
add sensor noise simulation to synthetic depth (inpainted) (ablation)depth-only scene parsing · SUN RGB-D val (inpainted depth)mIoU (w/o windows): 28.42 -> 34.86Improved
add sensor noise simulation to synthetic depth (raw) (ablation)depth-only scene parsing · SUN RGB-D val (raw depth)mIoU (w/o windows): 22.22 -> 30.95Improved
use proposed noise simulation instead of prior simulation (ablation)depth-only scene parsing · SUN RGB-D val (inpainted depth)mIoU (w/o windows): 32.61 -> 34.86Improved
add SceneNet to Pbrs synthetic training data (ablation)depth-adapted teacher · SUN RGB-D valmIoU: 29.24 -> 32.25Improved
add RGB student with first-stage depth-contour pseudo-labels (ablation)teacher · SUN RGB-D valmIoU: 32.25 -> 35.21Improved
add second integration stage with weak localization (ablation)first-stage pseudo-labels · SUN RGB-D valmIoU: 35.21 -> 43.53Improved
add first-stage depth cue to weak localization (ablation)second-stage-only labels · SUN RGB-D valmIoU: 25.97 -> 43.53Improved
add second stage on bed class (ablation)pseudo-label integration · SUN RGB-D valbed IoU: 54.93 -> 52.06Hurt
train student network on pseudo-labels instead of using pseudo-labels directlyscene parsing student · SUN RGB-D traineffective mIoU: 41.64 -> 49.46Improved
add UCM contour refinement at inference (ablation)Ours (Full) · SUN RGB-D valmIoU: 43.53 -> 43.80Improved
use weak image-level labels with depth adaptation instead of CYCADAscene parsing · SUN RGB-D valmIoU: 28.90 -> 43.53Improved

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