AI Paper Atlas

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

CCMN: A General Framework for Learning With Class-Conditional Multi-Label Noise

Ming-Kun Xie, Sheng-Jun Huang

TPAMI 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Partial and multi-label learning · 36 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 unbiased estimator (Hamming loss, Square) instead of baseline lossLh/Square, linear · yeast CCMNHamming loss: .280 -> .218Improved
use unbiased estimator (ranking, Sigmoid) instead of baseline lossLr/Sigmoid, linear · yeast CCMNranking loss: .261 -> .204Improved
use unbiased estimator (ranking, Sigmoid) instead of baseline lossLr/Sigmoid, linear · yeast CCMNaverage precision: .651 -> .720Improved
use unbiased estimator (ranking, Sigmoid) instead of baseline lossLr/Sigmoid, linear · scene CCMNaverage precision: .758 -> .809Improved
use unbiased estimator (ranking, Sigmoid) instead of baseline lossLr/Sigmoid, linear · mirflickr CCMNaverage precision: .823 -> .852Improved
use unbiased estimator (ranking, Sigmoid) instead of baseline lossLr/Sigmoid, MLP · scene CCMNaverage precision: .752 -> .816Improved
use unbiased estimator (Hamming, Hinge) instead of baseline lossLh/Hinge, MLP · mirflickr CCMNHamming loss: .124 -> .106Improved
use unbiased estimator uPML instead of PMLNIPML data · yeastHamming loss: .269 -> .210Improved
use unbiased estimator uPML instead of fPMLPML data · yeastHamming loss: .303 -> .208Improved
use uPML Lr instead of PMLNIPML data · enronaverage precision: .270 -> .563Improved
use uPML instead of PMLNIPML data · music_styleaverage precision: .723 -> .716Hurt

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