AI Paper Atlas

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

Learning to Infer Unseen Single-/ Multi-Attribute-Object Compositions With Graph Networks

Hui Chen, Jingjing Jiang, Nanning Zheng

TPAMI 2023 · Detection and segmentation › Open-set and few-shot detection · approach: Object-level representation learning · 13 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 graph-based attribute-object model instead of CGEunseen composition recognition · MIT-States (test)Test AUC@1: 5.1 -> 5.5Improved
use proposed model instead of CGE on UT-Zappos50Kcomposition recognition · UT-Zappos50K (test)Test AUC@1: 26.4 -> 33.5Improved
use proposed model instead of CGE on MADmulti-attribute recognition · MAD (test)Test AUC@1: 18.6 -> 21.4Improved
add decoding loss L_de (ablation)full model · UT-Zappos50K (test)Test AUC@1: 27.5 -> 33.5Improved
add balance loss L_bal (ablation)full model · UT-Zappos50K (test)Test AUC@1: 19.5 -> 33.5Improved
add attribute-object composer module (ablation)full model · MAD (test)Test AUC@1: 15.4 -> 21.4Improved
use contrastive fusion loss instead of L1 loss (ablation)fusion loss · MIT-States (test)Test AUC@1: 1.6 -> 5.5Improved
use proposed balance loss instead of alternative L_bal' (ablation)balance loss · MIT-States (test)Test AUC@1: 2.8 -> 5.5Improved
add graph message passing with trainable sparse random graph (ablation)linguistic encoder · UT-Zappos50K (test)Test AUC@1: 24.4 -> 33.5Improved
increase graph depth from 2 to 4 layers (ablation)graph network · UT-Zappos50K (test)Test AUC@1: 33.5 -> 28.6Hurt
use deeper visual backbone ResNet-101 instead of ResNet-18 (ablation)visual encoder · MIT-States (test)Test AUC@1: 5.5 -> 6.8Improved
use one-hot labels instead of GloVe (ablation)linguistic input · MIT-States (test)Test AUC@1: 5.5 -> 5.0Hurt

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