AI Paper Atlas

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

Decompositional Generation Process for Instance-Dependent Partial Label Learning

Congyu Qiao, Ning Xu, Xin Geng

ICLR 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Partial and multi-label learning · 1 citations (OpenAlex)

Read the paper

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
model candidate-label generation as instance-dependent categorical correct-label selection followed by Bernoulli incorrect-label selection, with MAP priorsPLL classification · MNISTaccuracy: 98.84±0.05% -> 98.92±0.05%Improved
model candidate-label generation as instance-dependent categorical correct-label selection followed by Bernoulli incorrect-label selection, with MAP priorsPLL classification · FMNISTaccuracy: 90.63±0.30% -> 91.48±0.32%Improved
model candidate-label generation as instance-dependent categorical correct-label selection followed by Bernoulli incorrect-label selection, with MAP priorsPLL classification · KMNISTaccuracy: 96.19±0.75% -> 96.88±0.17%Improved
model candidate-label generation as instance-dependent categorical correct-label selection followed by Bernoulli incorrect-label selection, with MAP priorsPLL classification · CIFAR-10accuracy: 86.37±0.38% -> 87.57±0.26%Improved
model candidate-label generation as instance-dependent categorical correct-label selection followed by Bernoulli incorrect-label selection, with MAP priorsPLL classification · CIFAR-100accuracy: 64.12±0.23% -> 64.59±0.17%Improved
use instance-dependent decompositional generation and MAP priorsPLL classification · Lostaccuracy: 76.87±0.86% -> 77.02±0.82%No clear effect
use instance-dependent decompositional generation and MAP priorsPLL classification · BirdSongaccuracy: 73.47±0.13% -> 74.23±0.17%Improved
use instance-dependent decompositional generation and MAP priorsPLL classification · MSRCv2accuracy: 49.97±0.43% -> 50.45±0.47%Improved
use instance-dependent decompositional generation and MAP priorsPLL classification · Soccer Playeraccuracy: 56.02±0.59% -> 55.99±0.28%Hurt
use instance-dependent decompositional generation and MAP priorsPLL classification · Yahoo!Newsaccuracy: 66.26±0.13% -> 66.62±0.19%Improved
add prior regularization and iteratively refine prior information (ablation)PL-ML · Lostaccuracy: 52.50±3.20% -> 77.02±0.82%Improved
add prior regularization and iteratively refine prior information (ablation)PL-ML · BirdSongaccuracy: 71.13±0.45% -> 74.23±0.17%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