AI Paper Atlas

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

Dual Student: Breaking the Limits of the Teacher in Semi-Supervised Learning

Zhanghan Ke, Daoye Wang, Qiong Yan, Jimmy Ren, Rynson W.H. Lau

ICCV 2019 · Label-efficient and robust learning › Semi-supervised learning · approach: Safe and realistic semi-supervised learning · 298 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
replace EMA teacher with a second independent student plus stabilization constraintMean Teacher · CIFAR-10 (1k labels)test error rate (%): 18.78 -> 15.74Improved
add stabilization constraint instead of plain consistency between students (ablation)Dual Student · CIFAR-10 (1k labels)test error rate (%): 17.38 -> 15.74Improved
use a confidence threshold xi=0.8 for stable samples (ablation)Dual Student · CIFAR-10 (1k labels)test error rate (%): 16.49 -> 15.74Improved
use a confidence threshold xi=0.4 for stable samples (ablation)Dual Student · CIFAR-100 (10k labels)test error rate (%): 33.67 -> 33.08Improved
train four students (Multiple Student) instead of twoDual Student · CIFAR-10 (1k labels)test error rate (%): 15.74 -> 14.97Improved
train eight students instead of fourMultiple Student · CIFAR-10 (1k labels)test error rate (%): 14.97 -> 14.77No clear effect
replace one student with a larger ResNet (Imbalanced Student)Dual Student · CIFAR-10 (1k labels)test error rate (%): 15.74 -> 12.39Improved
use the small 3.53M-param ResNet as stronger studentDual Student · CIFAR-10 (1k labels)test error rate (%): 15.74 -> 13.43Improved
apply Dual Student instead of Mean TeacherMean Teacher · ImageNet (10% labels, top-1)test error rate (%): 37.83 -> 36.48Improved
apply Dual Student instead of Mean TeacherMean Teacher · USPS to MNIST domain adaptationtop-1 accuracy (%): 80.41 -> 91.50Improved
use Dual Student instead of MT+FSWA with all labelsMT + FSWA · CIFAR-10 (all labels)test error rate (%): 5.14 -> 5.20Hurt
train Dual Student for 600 epochs instead of 300Dual Student · CIFAR-10 (1k labels)test error rate (%): 15.74 -> 14.17Improved

Later papers that compared with this method

2 later accepted papers report DualStudent as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

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