AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Transformer-Based Dual Relation Graph for Multi-Label Image Recognition

Jiawei Zhao, Ke Yan, Yifan Zhao, Xiaowei Guo, Feiyue Huang, Jia Li

ICCV 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Partial and multi-label learning · 106 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 Transformer structural relation (ablation)ResNet-101 baseline · MS-COCOmAP: 78.6 -> 82.9Improved
add Transformer structural relation (ablation)ResNet-101 baseline · VOC 2007mAP: 92.9 -> 94.3Improved
add cross-scale attention (ablation)Transformer structural relation · MS-COCOmAP: 82.9 -> 83.9Improved
add GCN semantic relation (ablation)ResNet-101 baseline · MS-COCOmAP: 78.6 -> 82.5Improved
add semantic-aware constraints (ablation)GCN semantic relation · MS-COCOmAP: 82.5 -> 83.5Improved
add Transformer to GCN (ablation)GCN semantic relation · VOC 2007mAP: 93.4 -> 94.6Improved
add 1/64 scale features (ablation)Transformer structural relation · MS-COCOmAP: 82.9 -> 83.1Improved
add 1/16 scale features (ablation)Transformer structural relation · MS-COCOmAP: 83.1 -> 83.3Improved
multiplication instead of summation in cross attention (ablation)cross-scale attention · MS-COCOmAP: 83.2 -> 83.9Improved
transformer units instead of MLP in cross-scale module (ablation)cross-scale attention · MS-COCOmAP: 83.3 -> 83.9Improved
learnable correlation matrix instead of static (ablation)semantic relation graph · MS-COCOmAP: 81.9 -> 82.5Improved
add structural guidance to joint correlation matrix (ablation)semantic relation graph · MS-COCOmAP: 82.5 -> 83.0Improved

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