AI Paper Atlas

Research map / Graph learning / GNN architectures

Efficient Relative Attribute Learning using Graph Neural Networks

Zihang Meng, Nagesh Adluru, Hyunwoo J. Kim, Glenn Fung, Vikas Singh

ECCV 2018 · Graph learning › GNN architectures · approach: Graph structure learning · 32 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 multi-task learning of all six attributes at once (ablation)Ours · OSR (mean)pairwise accuracy: 98.96 -> 99.20Improved
add multi-task learning of all 11 attributes at once (ablation)Ours · PubFig (mean)pairwise accuracy: 98.51 -> 98.55Improved
use group-of-images graph model with AlexNet instead of Souri et al. pairwise Siamese with VGGOurs · OSR (mean)pairwise accuracy: 97.77 -> 98.96Improved
use group-of-images graph model instead of Souri et al. pairwise SiameseOurs · PubFig (mean)pairwise accuracy: 94.52 -> 98.51Improved
use graph model with AlexNet instead of DeepPermNet with VGG, which needs ranked sequencesOurs · OSR (mean)pairwise accuracy: 98.48 -> 98.96Improved
use graph model instead of DeepPermNet with ranked sequencesOurs · PubFig (mean)pairwise accuracy: 98.14 -> 98.51Improved
use graph model instead of MG-CNN with group encoding for binary attributesOurs · Clothing Attributes Dataset (total)pairwise accuracy: 92.82 -> 92.39Hurt
use graph model instead of M-CNN without group informationOurs · Clothing Attributes Dataset (total)pairwise accuracy: 91.70 -> 92.39Improved
use graph model instead of MG-CNN on the Appearance groupOurs · Clothing Attributes Dataset (Appearance)pairwise accuracy: 91.93 -> 89.53Hurt
use graph model instead of MG-CNN on the Patterns groupOurs · Clothing Attributes Dataset (Patterns)pairwise accuracy: 95.37 -> 96.81Improved
use graph model instead of Souri et al. when pair labels barely overlapOurs · UT-Zappos50K-lexicon (mean)pairwise accuracy: 89.31 -> 90.07Improved
use multi-task graph model instead of single-attribute model on PubFig eyes (ablation)Ours (multi-task) · PubFig (eyes)pairwise accuracy: 98.62 -> 97.32Hurt

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