AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

AdaTransform: Adaptive Data Transformation

Zhiqiang Tang, Xi Peng, Tingfeng Li, Yizhe Zhu, Dimitris N. Metaxas

ICCV 2019 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Optimization-based domain generalization · 21 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 AdaCutout instead of fixed CutoutResNet32 · CIFAR-10 (10% train)accuracy: 77.21 -> 78.02Improved
add AdaCutout instead of fixed CutoutResNet32 · CIFAR-100 (10% train)accuracy: 40.41 -> 41.02Improved
add AdaErasing instead of random ErasingResNet32 · CIFAR-10 (10% train)accuracy: 77.25 -> 78.12Improved
add AdaErasing instead of random ErasingResNet32 · CIFAR-100 (10% train)accuracy: 40.53 -> 41.21Improved
use adaptive texture transformation instead of random augmentation (ablation)two stacked hourglasses · MPII Human Posemean PCKh: 88.1 -> 88.7Improved
use adaptive cutout instead of random augmentation (ablation)two stacked hourglasses · MPII Human Posemean PCKh: 88.1 -> 88.6Improved
use adaptive scale and rotation instead of random augmentation (ablation)two stacked hourglasses · MPII Human Posemean PCKh: 88.1 -> 88.9Improved
combine all adaptive transformations (AdaAll) (ablation)two stacked hourglasses · MPII Human Posemean PCKh: 88.1 -> 89.3Improved
use AdaImgTexture instead of random augmentation under texture perturbationtwo stacked hourglasses · MPII Human Pose (texture-perturbed test)mean PCKh: 86.3 -> 87.8Improved
use AdaTransform instead of AdvAugtwo stacked hourglasses · 300-W Full SetNME: 3.28 -> 3.24Improved
use AdaTransform instead of AdvAugtwo stacked hourglasses · LSP testmean PCK: 92.5 -> 92.9Improved
use AdaTransform instead of AutoAugmentShake-Shake · CIFAR-10 (full train)error (%): 1.99 -> 2.11Hurt

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