AI Paper Atlas

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

Unsupervised Meta-Learning of Figure-Ground Segmentation via Imitating Visual Effects

Ding-Jie Chen, Jui-Ting Chien, Hwann-Tzong Chen, Tyng-Luh Liu

AAAI 2019 · Detection and segmentation › Open-set and few-shot detection · approach: Amodal and open-world instance segmentation · 3 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 VEGAN instead of the strongest listed unsupervised baseline, CAfigure-ground segmentation · MSRA500mean IoU: 0.67 -> 0.76Improved
use VEGAN instead of the strongest listed unsupervised baseline, MSTfigure-ground segmentation · GC50mean IoU: 0.60 -> 0.58Hurt
use VEGAN instead of the strongest listed unsupervised baseline, CAfigure-ground segmentation · ECSSDmean IoU: 0.50 -> 0.58Improved
use VEGAN instead of the strongest listed unsupervised baseline, CAfigure-ground segmentation · Flower17mean IoU: 0.72 -> 0.72No clear effect
use VEGAN instead of the strongest listed unsupervised baseline, CAfigure-ground segmentation · Flower102mean IoU: 0.75 -> 0.81Improved
use VEGAN instead of the strongest listed unsupervised baseline, MSTfigure-ground segmentation · CUB200mean IoU: 0.54 -> 0.52Hurt
replace the base generator with pre-trained ResNet (ablation)VEGAN B4, black background · MSRA500mean IoU: 0.76 -> 0.73Hurt
add skip-layers and bilinear upsampling while retaining patchGAN (ablation)VEGAN B4, black background · MSRA500mean IoU: 0.76 -> 0.70Hurt
use full-image discriminator with skip-layers and bilinear upsampling rather than patchGAN without those modifications (ablation)VEGAN, black background · MSRA500mean IoU: 0.67 -> 0.76Improved
replace the base generator with pre-trained ResNet (ablation)VEGAN C4, color selectivo · MSRA500mean IoU: 0.75 -> 0.73Hurt
add skip-layers and bilinear upsampling while retaining patchGAN (ablation)VEGAN C4, color selectivo · MSRA500mean IoU: 0.75 -> 0.74Hurt
replace the base generator with pre-trained ResNet (ablation)VEGAN D4, defocus/Bokeh · MSRA500mean IoU: 0.73 -> 0.66Hurt

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