AI Paper Atlas

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

Deep Co-Training for Semi-Supervised Image Recognition

Siyuan Qiao, Wei Shen, Zhishuai Zhang, Bo Wang, Alan Yuille

ECCV 2018 · Label-efficient and robust learning › Semi-supervised learning · approach: GAN-based semi-supervised learning · 554 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
increase number of views from 2 to 4 (ablation)Deep Co-Training · CIFAR-10 (4000 labeled)error rate (%): 9.03 -> 8.54Improved
increase number of views from 4 to 8 (ablation)Deep Co-Training · CIFAR-10 (4000 labeled)error rate (%): 8.54 -> 8.35Improved
increase number of views from 2 to 4 (ablation)Deep Co-Training · SVHN (1000 labeled)error rate (%): 3.61 -> 3.38Improved
increase number of views from 4 to 8 (ablation)Deep Co-Training · SVHN (1000 labeled)error rate (%): 3.38 -> 3.29Improved
add view difference loss L_dif (adversarial examples) to co-training loss (ablation)Deep Co-Training · SVHN (1000 labeled)validation accuracyImproved
add L_dif (ablation)Deep Co-Training · CIFAR-10 (4000 labeled)validation accuracyImproved
add data augmentation (ablation)dual-view Deep Co-Training · CIFAR-100 (10000 labeled)error rate (%): 38.77 -> 34.63Improved
use Deep Co-Training instead of Temporal EnsemblingCIFAR-100+ · CIFAR-100+ (10000 labeled, with augmentation)error rate (%): 38.65 -> 34.63Improved
use Deep Co-Training instead of Mean Teacher (ResNet-18)ImageNet 10% labeled · ImageNet val (10% labeled)top-1 error rate (%): 49.07 -> 46.50Improved
add unlabeled data via Deep Co-TrainingResNet-18 10% supervised · ImageNet val (10% labeled)top-1 error rate (%): 52.23 -> 46.50Improved
use dual-view Deep Co-Training instead of VATSVHN/CIFAR-10 · CIFAR-10 (4000 labeled)error rate (%): 10.55 -> 9.03Improved

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