AI Paper Atlas

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

Spatial Mixture Models with Learnable Deep Priors for Perceptual Grouping

Jinyang Yuan, Bin Li, Xiangyang Xue

AAAI 2019 · Detection and segmentation › Open-set and few-shot detection · approach: Object-centric learning theory and video · 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
use learnable deep priors with disentangled shape weights, appearance components, and a complementary background componentPerceptual grouping on Multi-Shapes · Multi-Shapes 28×28, 3 objectsAMI: 0.875 -> 0.941Improved
use learnable deep priors with disentangled shape weights, appearance components, and a complementary background componentPerceptual grouping on Multi-Shapes · Multi-Shapes 28×28, 3 objectsMSE: 1.10 × 10^{-2} -> 0.28e-2Improved
replace truncated stick-breaking weights with softmax weights (ablation)Proposed method · Multi-Shapes 28×28, 3 objectsAMI: 0.941 -> 0.875Hurt
replace truncated stick-breaking weights with softmax weights (ablation)Proposed method · Multi-Shapes 28×28, 3 objectsMSE: 0.28e-2 -> 1.10 × 10^{-2}Hurt
train on 3-object scenes and evaluate on scenes with fewer objectsProposed method · Multi-Shapes, 2 objectsAMI: 0.906 -> 0.961Improved
train on 3-object scenes and evaluate on scenes with more objectsProposed method · Multi-Shapes, 4 objectsAMI: 0.838 -> 0.901Improved
use Gaussian rather than Bernoulli mixture components (ablation)Proposed method · Multi-Shapes 28×28, 3 objects, F=64, N=64AMI: 0.941 -> 0.939No clear effect
use Gaussian rather than Bernoulli mixture components (ablation)Proposed method · Multi-Shapes 28×28, 3 objects, F=64, N=64MSE: 0.28e-2 -> 0.29e-2No clear effect

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