AI Paper Atlas

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

Enhancing Sample Utilization through Sample Adaptive Augmentation in Semi-Supervised Learning

Guan Gui, Zhen Zhao, Lei Qi, Luping Zhou, Lei Wang, Yinghuan Shi

ICCV 2023 · Label-efficient and robust learning › Semi-supervised learning · approach: Confidence-based pseudo-label selection · 13 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 SAA to FixMatchFixMatch · CIFAR-10 (40 labels)accuracy (%): 92.50 -> 94.76Improved
add SAA to FlexMatchFlexMatch · CIFAR-10 (40 labels)accuracy (%): 95.01 -> 95.31Improved
add SAA to FixMatchFixMatch · STL-10 (1000 labels)accuracy (%): 85.27 -> 87.92Improved
add SAA to FlexMatchFlexMatch · SVHN (40 labels)accuracy (%): 92.42 -> 93.15Improved
apply diverse augmentation to all samples instead of only naive samples (ablation)FixMatch + SAA · STL-10 (1000 labels)accuracy (%): 85.27 -> 83.19Hurt
apply diverse augmentation to all samples (ablation)FixMatch · CIFAR-10 (40 labels)accuracy (%): 92.50 -> 92.98No clear effect
apply diverse augmentation to random 50% samples (ablation)FixMatch · CIFAR-10 (40 labels)accuracy (%): 92.50 -> 94.05Mixed
select naive samples with OTSU instead of fixed proportion (25%) (ablation)SAA on FixMatch · CIFAR-10 (40 labels)accuracy (%): 93.10 -> 94.50Improved
select naive samples with OTSU instead of fixed threshold (ablation)SAA on FixMatch · STL-10 (1000 labels)accuracy (%): 85.98 -> 87.92Improved
add model warm-up of 100k iterations before applying SAA (ablation)SAA on FixMatch · CIFAR-10 (40 labels)accuracy (%)Improved
augment whole image then cut, instead of cutting then augmenting patches (ablation)SAA · CIFAR-10 (40 labels) and STL-10accuracy (%)Improved
add SAA to FixMatch: speed of improvementFixMatch · CIFAR-10 (40 labels), 200k iterationsaccuracy (%): 86.72 -> 91.15Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 4 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