AI Paper Atlas

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

Disambiguated Attention Embedding for Multi-Instance Partial-Label Learning

Wei Tang, Weijia Zhang, Min-Ling Zhang

NeurIPS 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Partial and multi-label learning · 5 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 attention loss (ablation)DEAM · FMNIST-MIPL, r=1accuracy: 0.744 -> 0.881Improved
add attention loss (ablation)DEAM · FMNIST-MIPL, r=3accuracy: 0.586 -> 0.657Improved
add attention loss (ablation)DEAM · SIVAL-MIPL, r=1accuracy: 0.607 -> 0.635Improved
add attention loss (ablation)DEAM · SIVAL-MIPL, r=3accuracy: 0.499 -> 0.503No clear effect
momentum-based disambiguation vs lambda=0 (progressive, current classifier output) variant (ablation)DEAM · MNIST/FMNIST/Birdsong-MIPL, larger raccuracyImproved
momentum-based disambiguation vs lambda=1 (uniform weights) variant (ablation)DEAM · MNIST/FMNIST/Birdsong-MIPL, larger raccuracyImproved
uniform weights (lambda=1) instead of progressive (lambda=0) at r=3 (ablation)DEAM variants · MNIST-MIPL and FMNIST-MIPLaccuracyMixed
vary attention-loss weight lambda_a (ablation)DEAM · MNIST-MIPL and CRC-MIPLaccuracyNo clear effect
use DEAM instead of MIPLGP on benchmark datasetsMIPL algorithm · MNIST/FMNIST/Birdsong-MIPL, r=1accuracy: 0.949 -> 0.976Improved
use DEAM instead of MIPLGP on SIVAL-MIPLMIPL algorithm · SIVAL-MIPL, r=1accuracy: 0.669 -> 0.635Hurt
use DEAM instead of MIPLGP on larger rMIPL algorithm · MNIST-MIPL, r=2accuracy: 0.817 -> 0.943Improved
use DEAM instead of PLL algorithm AGGD (MaxMin) on CRC-MIPL-SIFTMIPL algorithm · CRC-MIPL-SIFTaccuracy: 0.285 -> 0.532Improved

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