AI Paper Atlas

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

Unsupervised Segmentation in Real-World Images via Spelke Object Inference

Honglin Chen, Rahul Venkatesh, Yoni Friedman, Jiajun Wu, Joshua B. Tenenbaum, Daniel L. K. Yamins, Daniel M. Bear

ECCV 2022 · Detection and segmentation › Open-set and few-shot detection · approach: Unsupervised object and part discovery · 23 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 excitatory messages to KProp (ablation)EISEN · TDW-Playroom val (motion supervision)mIoU: 0.036 -> 0.730Improved
add inhibitory messages to KProp (ablation)EISEN · TDW-Playroom val (motion supervision)mIoU: 0.036 -> 0.730Improved
use l2 normalization instead of softmax in KProp (ablation)EISEN · TDW-Playroom val (motion supervision)mIoU: 0.036 -> 0.730Improved
use Competition readout instead of argmax (ablation)EISEN · TDW-Playroom val (motion supervision)mIoU: 0.676 -> 0.730Improved
add long-range affinity pairs to local pairs (ablation)EISEN · TDW-Playroom val (motion supervision)mIoU: 0.700 -> 0.730Improved
use all affinity pairs instead of local plus sampled long-range (ablation)EISEN · TDW-Playroom val (motion supervision)mIoU: 0.730 -> 0.732No clear effect
increase KProp iterations from 10 to 40 (ablation)EISEN · TDW-Playroom val (motion supervision)mIoU: 0.389 -> 0.730Improved
increase Competition iterations from 1 to 3 (ablation)EISEN · TDW-Playroom val (motion supervision)mIoU: 0.729 -> 0.730No clear effect
add bootstrapping rounds (round 1 to round 3)EISEN · BridgemIoU: 0.336 -> 0.551Improved
add bootstrapping rounds (round 1 to round 3)Mask-RCNN · BridgemIoU: 0.053 -> 0.102Improved
add bootstrapping rounds (round 1 to round 3)Panoptic DeepLab · BridgemIoU: 0.051 -> 0.057No clear effect
replace full supervision with motion-only supervisionPanoptic DeepLab · TDW-Playroom valmIoU: 0.870 -> 0.620Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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