AI Paper Atlas

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

Unsupervised Object-Centric Learning From Multiple Unspecified Viewpoints

Jinyang Yuan, Tonglin Chen, Zhimeng Shen, Bin Li, Xiangyang Xue

TPAMI 2024 · Detection and segmentation › Open-set and few-shot detection · approach: Object-centric learning theory and video · 0 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 explicit shadow modeling (ablation)OCLOC · CLEVR & SHOP Test 1ARI-A: 0.395 -> 0.734Improved
add explicit shadow modeling (ablation)OCLOC · GSO & ShapeNet Test 1ARI-A: 0.429 -> 0.831Improved
add explicit shadow modeling (ablation)OCLOC · GSO & ShapeNet Test 1IoU: 0.514 -> 0.707Improved
add explicit shadow modeling (ablation)OCLOC · GSO & ShapeNet Test 1OCA: 0.000 -> 0.715Improved
add explicit shadow modeling (ablation)OCLOC · CLEVR & SHOP Test 1ARI-O: 0.903 -> 0.859Hurt
add explicit shadow modeling (ablation)OCLOC · CLEVR & SHOP Test 2ARI-A: 0.265 -> 0.545Improved
order viewpoints as video for SAVi instead of unorderedSAVi · CLEVR & SHOP Test 1ARI-O: 0.046 -> 0.715Improved
use OCLOC without viewpoint annotations instead of annotated MulMONOCLOC · CLEVR & SHOP Test 1ARI-A: 0.473 -> 0.734Improved
use OCLOC instead of MulMONOCLOC · CLEVR & SHOP Test 1OCA: 0.227 -> 0.205Hurt
use OCLOC instead of SIMONeOCLOC · GSO & ShapeNet Test 1ARI-A: 0.404 -> 0.831Improved
test with more objects (7-10, K=11) than Test 1OCLOC · CLEVR & SHOPARI-A: 0.734 -> 0.545Hurt
test with more objects (7-10, K=11) than Test 1OCLOC · GSO & ShapeNetARI-A: 0.831 -> 0.708Hurt

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