AI Paper Atlas

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

Repetitive Reprediction Deep Decipher for Semi-Supervised Learning

Guo-Hua Wang, Jianxin Wu

AAAI 2020 · Label-efficient and robust learning › Semi-supervised learning · approach: Confidence-based pseudo-label selection · 31 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
Use R2-D2 rather than Dual-View Deep Co-TrainingImageNet validation with ResNet-18 · ImageNet validation, 10% labeledTop-1 error rate (%): 46.50 -> 41.55Improved
Use R2-D2 rather than DCTCIFAR-100 with ConvLarge · CIFAR-100 test, 10,000 labeledError rate (%): 34.63 ± 0.14 -> 32.87 ± 0.51Improved
Use R2-D2 rather than HybridNetCIFAR-10 with Shake-Shake · CIFAR-10 test, 4,000 labeledError rate (%): 6.09 -> 5.72 ± 0.06Improved
Use R2-D2 rather than DCT with 8 ViewsSVHN with ConvLarge · SVHN test, 1,000 labeledError rate (%): 3.29 ± 0.03 -> 3.64 ± 0.20Hurt
Repeat the second stage without reprediction or learning-rate reduction (ablation)D2 on CIFAR-10 · CIFAR-10 test, 4,000 labeledError rate (%): 6.71 -> 6.37Improved
Add reprediction while repeating the second stage, without reducing the learning rate (ablation)D2 on CIFAR-10 · CIFAR-10 test, 4,000 labeledError rate (%): 6.37 -> 6.23Improved
Reduce the learning rate while repeating the second stage, without reprediction (ablation)D2 on CIFAR-10 · CIFAR-10 test, 4,000 labeledError rate (%): 6.71 -> 5.94Improved
Add both reprediction and learning-rate reduction to repeated second-stage training (ablation)D2 on CIFAR-10 · CIFAR-10 test, 4,000 labeledError rate (%): 5.94 -> 5.78Improved
Set α=0.2 rather than α=0.1 with β=0.03 (ablation)R2-D2 on CIFAR-10 · CIFAR-10 test, 4,000 labeledError rate (%): 5.78 -> 5.44Improved
Vary α from 0.1 through 0.5 with β=0.03 (ablation)R2-D2 on CIFAR-10 · CIFAR-10 test, 4,000 labeledError rate (%): 5.78; 5.44; 5.81; 5.90; 6.11Mixed
Vary β from 0.01 through 0.05 with α=0.1 (ablation)R2-D2 on CIFAR-10 · CIFAR-10 test, 4,000 labeledError rate (%): 5.62; 5.75; 5.78; 5.83; 5.76No clear effect
Replace forward KL with reverse KL as the consistency loss (ablation)R2-D2 on CIFAR-10 · CIFAR-10 test, 4,000 labeledError rate (%): 5.78 -> 8.06Hurt

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