AI Paper Atlas

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

Transductive Semi-Supervised Deep Learning using Min-Max Features

Weiwei Shi, Yihong Gong, Chris Ding, Zhiheng MaXiaoyu Tao, Nanning Zheng

ECCV 2018 · Label-efficient and robust learning › Semi-supervised learning · approach: Safe and realistic semi-supervised learning · 224 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 confidence levels on unlabeled samples (ablation)TSSDL · CIFAR10 (1000 labels)top-1 error rate (%): 50.38 -> 21.13Improved
add confidence levels on unlabeled samples (ablation)TSSDL · CIFAR10 (4000 labels)top-1 error rate (%): 18.10 -> 10.90Improved
add confidence levels on unlabeled samples (ablation)TSSDL · SVHN (250 labels)top-1 error rate (%): 46.74 -> 5.02Improved
add confidence levels on unlabeled samples (ablation)TSSDL · SVHN (1000 labels)top-1 error rate (%): 10.10 -> 3.80Improved
add MMF regularization to the plain transductive DCNN (ablation)TDCNN · CIFAR10 (4000 labels)top-1 error rate (%): 16.17 -> 13.11Improved
add RF regularization to the plain transductive DCNN (ablation)TDCNN · CIFAR10 (4000 labels)top-1 error rate (%): 16.17 -> 13.30Improved
add RF regularization on top of MMF (ablation)TMMF · CIFAR10 (4000 labels)top-1 error rate (%): 13.11 -> 10.90Improved
add MMF regularization on top of RF (ablation)TRF · SVHN (250 labels)top-1 error rate (%): 9.93 -> 5.02Improved
add MMF to RF with all labeled SVHN data (ablation)TRF · SVHN (73257 labels)top-1 error rate (%): 2.65 -> 2.42Improved
add MMF regularization to the plain transductive DCNN (ablation)TDCNN · SVHN (500 labels)top-1 error rate (%): 13.79 -> 7.23Improved
use unlabeled data via TSSDL instead of fully supervised trainingFully Supervised · CIFAR10 (1000 labels)top-1 error rate (%): 46.43 -> 21.13Improved
combine TSSDL with Mean TeacherTSSDL · CIFAR10 (1000 labels)top-1 error rate (%): 21.13 -> 18.41Improved

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