AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Visiting the Invisible: Layer-by-Layer Completed Scene Decomposition

Chuanxia Zheng, Duy-Son Dao, Guoxian Song, Tat‐Jen Cham, Jianfei Cai

IJCV 2021 · Detection and segmentation › Open-set and few-shot detection · approach: Amodal and open-world instance segmentation · 20 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
train decomposition and completion jointly instead of separately (ablation)CSDNet (PICNet-patch, HTC) · CSD testmask AP: 43.8 -> 50.3Improved
add scene completion between decomposition steps (ablation)CSDNet (HTC) · CSD testmask AP: 36.8 -> 50.3Improved
use patch attention instead of point attention in completion (ablation)CSDNet (joint training) · CSD testmask AP: 47.7 -> 50.3Improved
use HTC instead of Mask-RCNN as decomposition network (ablation)CSDNet completion · CSD completionPSNR: 27.31 -> 30.45Improved
train completion jointly with HTC decomposition instead of separately (ablation)CSDNet completion · CSD completionPSNR: 26.75 -> 30.45Improved
replace one-pass HTC with layer-by-layer CSDNetHTC · CSD testmask AP: 47.3 -> 50.3Improved
use ground-truth completed images (oracle) in each stepCSDNet (HTC) · CSD testmask AP: 50.3 -> 56.0Improved
switch backbone from Mask-RCNN to HTCCSDNet · CSD testmask AP: 48.7 -> 50.3Improved
order by predicted layer order instead of mask area (ablation)CSDNet · CSD testOAP: 44.7 -> 81.7Improved
order by predicted layer order instead of y-axis position (ablation)CSDNet · CSD testOAP: 62.0 -> 81.7Improved
use CSDNet instead of MLC with HTC segmentationamodal segmentation · COCOAmAP: 34.4 -> 34.8Improved
use CSDNet instead of MLC with HTC segmentationamodal segmentation · KINSmAP: 31.6 -> 32.2Improved

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