AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Augmentation-invariant Learning Strategy via Data Augmentation for Improving Model Generalization

Yu Miao, Juanjuan Zhao, Sijie Song, Ran Gong, Yuanqian Zhu, Lusha Qi, Yan Qiang

AAAI 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Data augmentation and generalization bias · 0 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 AILS to MobileNetV3MobileNetV3 · MedMNIST+ 2D (backbone study)accuracy (%): 70.1 -> 76.3Improved
add AILS to ResNeSt-101ResNeSt-101 · MedMNIST+ 2D (backbone study)accuracy (%): 80.3 -> 85.1Improved
add AILS to Swin-TinySwin-Tiny · MedMNIST+ 2D (backbone study)accuracy (%): 80.5 -> 84.4Improved
add AILS reduces epochs to convergenceResNeSt-101 · MedMNIST+ 2D (backbone study)epochs to convergence: 65 -> 53Improved
replace BSDA with AILSAILS vs BSDA · PneumoniaMNISTaccuracy (%): 88.8 -> 92.2Improved
replace BSDA with AILSAILS vs BSDA · TissueMNISTaccuracy (%): 73.3 -> 79.3Improved
replace BSDA with AILSAILS vs BSDA · BloodMNISTaccuracy (%): 98.8 -> 98.9No clear effect
use AILS with 20% training data instead of BSDAAILS vs BSDA · MedMNIST+ 2D avg (20% training data)accuracy (%): 67.2 -> 69.4Improved
use AILS with 50% training data instead of BSDAAILS vs BSDA · MedMNIST+ 2D avg (50% training data)accuracy (%): 74.1 -> 81.8Improved
lower augmentation intensity alpha from 0.3 to 0.1 (ablation)AILS · MedMNIST+ 2D (9 subsets, avg)accuracy (%): 85.74 -> 79.84Hurt
raise augmentation intensity alpha from 0.3 to 0.7 (ablation)AILS · MedMNIST+ 2D (9 subsets, avg)accuracy (%): 85.74 -> 76.04Hurt
lower KL weight beta from 1.0 to 0.1 (ablation)AILS · MedMNIST+ 2D (9 subsets, avg)accuracy (%): 85.74 -> 78.24Hurt

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