AI Paper Atlas

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

Adversarial Data Augmentation via Deformation Statistics

Sahin Olut, Zhengyang Shen, Zhenlin Xu, Samuel Gerber, Marc Niethammer

ECCV 2020 · Label-efficient and robust learning › Semi-supervised learning · approach: Semi-supervised medical segmentation · 12 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 adversarial direction to EigAug (rand r) (ablation)EigAug · OAI knee MRI, 4 training samplesDice (%): 73.3 -> 78.4Improved
add adversarial direction to EigAug (rand r) (ablation)EigAug · OAI knee MRI, 8 training samplesDice (%): 76.2 -> 81.0Improved
add adversarial direction to EigAug (fixed r=2) (ablation)EigAug · OAI knee MRI, 4 training samplesDice (%): 73.6 -> 76.1Improved
add adversarial direction to EigAug (fixed r=2) (ablation)EigAug · OAI knee MRI, 8 training samplesDice (%): 77.7 -> 78.7Improved
randomize deformation magnitude r~U(1.5,3) instead of fixed r=2 (ablation)AdvEigAug · OAI knee MRI, 4 training samplesDice (%): 76.1 -> 78.4Improved
randomize deformation magnitude r~U(1.5,3) instead of fixed r=2 (ablation)AdvEigAug · OAI knee MRI, 8 training samplesDice (%): 78.7 -> 81.0Improved
use fixed r=3 instead of r=2 (ablation)AdvEigAug · OAI knee MRI, 8 training samplesDice (%): 78.7 -> 76.9Hurt
use LDDMM deformation model instead of displacement field network (ablation)AdvEigAug rand r · OAI knee MRI, 4 training samplesDice (%): 78.4 -> 78.5Improved
use online instead of offline augmentation with LDDMM (ablation)L-AdvEigAug rand r · OAI knee MRI, 4 training samplesDice (%): 78.5 -> 79.1Improved
use online instead of offline augmentation with displacement model (ablation)AdvEigAug rand r · OAI knee MRI, 8 training samplesDice (%): 81.0 -> 81.1No clear effect
use adversarial statistical-deformation augmentation instead of AdvAffineAdvAffine · OAI knee MRI, 4 training samplesDice (%): 75.1 -> 79.1Improved
add adversarial AdvEigAug augmentation vs no augmentation3D U-Net · OAI knee MRI, 4 training samplesDice (%): 75.2 -> 79.1Improved

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