AI Paper Atlas

Research map / Label-efficient and robust learning / Semi-supervised learning

Newton-coupled Dual-Teacher Semi-supervised Learning Framework

Hongyang He, Xinyuan Song, Yan Zhong, Daizong Liu, Xuanyu Liu, Victor Sanchez

ICML 2026 · Label-efficient and robust learning › Semi-supervised learning · approach: Confidence-based pseudo-label selection · 0 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
add Newton-guided update (ablation)TTN · CIFAR-10 (4k labels)accuracy: 89.8 -> 97.5Improved
add confidence-weighted dual-teacher fusion (ablation)TTN · CIFAR-10 (4k labels)accuracy: 91.2 -> 97.5Improved
add MAE as second teacher to DINOv3 teacher (ablation)TTN · CIFAR-10 (4k labels)accuracy: 91.0 -> 97.5Improved
add augmentation consistency loss (ablation)TTN · CIFAR-10 (4k labels)accuracy: 92.3 -> 97.5Improved
use confidence-based Hessian fusion instead of equal fusion (ablation)TTN · CIFAR-10 (4k labels)accuracy: 92.0 -> 97.5Improved
use fused curvature Newton step instead of identity Hessian (ablation)TTN · CIFAR-10 (4k labels)accuracy: 90.8 -> 97.5Improved
add Newton-guided update (ablation)TTN · CIFAR-10 convergencesteps to 85% accuracy: 4.8k -> 2.2k stepsImproved
add Newton-guided update (ablation)TTN · CIFAR-100final accuracy: 80.0 -> 81.4Improved
pair MAE with DINOv3 teachers versus baseline (ablation)TTN · ImageNet (25% labels)accuracy gain: 3.4% improvementImproved
pair MAE with DINOv2 teachers (ablation)TTN · ImageNet (25% labels)accuracy gain: 3.1%Improved
use TTN instead of TRiCoTTN · SVHN (1k labels)accuracy: 94.2 -> 93.6Hurt
use TTN instead of TRiCoTTN · ImageNet (10% labels)accuracy: 85.9 -> 85.7No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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