AI Paper Atlas

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

Universal Sketch Perceptual Grouping

Ke Li, Kaiyue Pang, Jifei Song, Yi-Zhe Song, Tao Xiang, Timothy M. Hospedales, Honggang Zhang

ECCV 2018 · Detection and segmentation › Open-set and few-shot detection · approach: Object-level representation learning · 57 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 the global grouping loss (ablation)Ours · SPG seen categoriesVOI (lower is better): 0.63 -> 0.59Improved
add the global grouping loss (ablation)Ours · SPG unseen categoriesVOI (lower is better): 0.71 -> 0.64Improved
add the local grouping loss (ablation)Ours · SPG seen categoriesVOI (lower is better): 0.75 -> 0.59Improved
add the local grouping loss (ablation)Ours · SPG unseen categoriesVOI (lower is better): 0.95 -> 0.64Improved
add the reconstruction (generative) loss (ablation)Ours · SPG seen categoriesVOI (lower is better): 0.68 -> 0.59Improved
add the reconstruction (generative) loss (ablation)Ours · SPG unseen categoriesVOI (lower is better): 0.86 -> 0.64Improved
add the reconstruction (generative) loss (ablation)Ours · SPG unseen categoriessegmentation covering (SC): 0.69 -> 0.77Improved
add an l2 loss on the affinity matrix in place of separate local and global grouping losses (ablation)Ours · SPG seen categoriesVOI (lower is better): 0.59 -> 2.68Hurt
use the proposed grouper instead of Edge-PGOurs · SPG unseen categoriesVOI (lower is better): 1.13 -> 0.64Improved
use the proposed grouper instead of Edge-PGOurs · Edge-PG datasets (unseen dataset)VOI (lower is better): 1.69 -> 0.96Improved
use the proposed grouper instead of DeepLabOurs · SPG seen categoriesVOI (lower is better): 1.20 -> 0.59Improved
train FG-SBIR on sketches synthesised with the proposed grouper instead of LDSAFG-SBIR pipeline · FG-SBIR Shoe-V2top-1 accuracy: 21.17% -> 26.88%Improved

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