AI Paper Atlas

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

General Partial Label Learning via Dual Bipartite Graph Autoencoder

Brian Chen, Bo Wu, Alireza Zareian, Hanwang Zhang, Shih-Fu Chang

AAAI 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Partial and multi-label learning · 11 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 DB-GAE instead of the strongest baseline, PL-LEAFGPLL face naming · MPII-MDF1-score: 0.610 -> 0.768Improved
Use DB-GAE instead of the strongest baseline, SUREGPLL face naming · MPII-MDAccuracy: 48.7 % -> 76.5 %Improved
Use DB-GAE instead of the strongest baseline, PL-AGGDPLL face naming · M-VADAccuracy: 86.5 % -> 90.3 %Improved
Add Graph Autoencoder (ablation)DB-GAE · MPII-MDF1-score: 0.614 -> 0.768Improved
Add Graph Autoencoder (ablation)DB-GAE · MPII-MDAccuracy: 62.9% -> 76.5%Improved
Add Graph Autoencoder (ablation)DB-GAE · M-VADAccuracy: 81.6% -> 90.3%Improved
Add Dual Bipartite Graph architecture (ablation)DB-GAE · MPII-MDAccuracy: 68.4 % -> 76.5 %Improved
Add Dual Bipartite Graph architecture (ablation)DB-GAE · M-VADAccuracy: 88.3 % -> 90.3 %Improved
Add Cross-Group Link (ablation)DB-GAE · MPII-MDF1-score: 0.730 -> 0.768Improved
Add Cross-Group Link (ablation)DB-GAE · M-VADAccuracy: 89.2 % -> 90.3 %Improved
Add Graph Attention (ablation)DB-GAE · MPII-MDF1-score: 0.743 -> 0.768Improved
Add Graph Attention (ablation)DB-GAE · M-VADAccuracy: 87.3 % -> 90.3 %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