AI Paper Atlas

Research map / Label-efficient and robust learning / Noisy labels

Bridging Generative and Discriminative Noisy-Label Learning via Direction-Agnostic EM Formulation

Fengbei Liu, Chong Wang, Yuanhong Chen, Yuyuan Liu, Gustavo Carneiro

TPAMI 2026 · Label-efficient and robust learning › Noisy labels · approach: Instance-dependent noise modeling · 3 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 uncertainty component to coverage-only prior (ablation)PLS prior · CIFAR-10 IDN 50%accuracy (%): 78.38 -> 90.57Improved
add coverage component to uncertainty-only prior (ablation)PLS prior · CIFAR-10 IDN 50%accuracy (%): 66.61 -> 90.57Improved
add EMA moving average (beta 0.9) to coverage (ablation)PLS prior · CIFAR-10 IDN 50%accuracy (%): 61.47 -> 90.57Improved
use stochastic sampling instead of argmax for coverage (ablation)PLS prior · CIFAR-10 IDN 50%accuracy (%): 15.26 -> 90.57Improved
use GMM-based noise probability instead of random w_i (ablation)PLS prior · CIFAR-10 IDN 50%accuracy (%): 84.28 -> 90.57Improved
add E-step KL divergence (ablation)EM objective · CIFAR-10 IDN 50%accuracy (%): 80.46 -> 90.57Improved
use L_PRI instead of soft cross-entropy on partial labels (ablation)EM objective · CIFAR-10 IDN 50%accuracy (%): 73.72 -> 90.57Improved
use reverse KL instead of original KL for L_PRI (ablation)EM objective · CIFAR-10 IDN 50%accuracy (%): 88.47 -> 90.57Improved
raise moving-average beta from 0.5 to 0.9 (ablation)PLS prior · CIFAR-10 IDN 50%accuracy (%): 85.73 -> 90.57Improved
increase K from 1 to 3 label samples (ablation)EM objective · CIFAR-10 IDN 50%accuracy (%): 90.57 -> 89.75No clear effect
add full EM with PLS instead of noisy labels only (CE) (ablation)noisy-label classifier · CIFAR-10 IDN 50%accuracy (%): 58.93 -> 90.57Improved
use p(X|Y) instead of p(Y|X) objectiveEM objective · CIFAR-10 IDN 50%accuracy (%): 89.77 -> 90.57 (CIFAR-10 IDN 50%); 54.53 -> 53.34 (Red Mini-ImageNet 20%)Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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