AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

Faster AutoAugment: Learning Augmentation Strategies Using Backpropagation

Ryuichiro Hataya, Zdenek Jan, Kazuki Yoshizoe, Hideki Nakayama

ECCV 2020 · Architectures and efficiency › Neural architecture search · approach: AutoML pipeline search · 210 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
replace AutoAugment search with differentiable adversarial search (Faster AA)AutoAugment · CIFAR-10 search costGPU hours: 5,000 -> 0.23Improved
replace AutoAugment search with differentiable adversarial search (Faster AA)AutoAugment · ImageNet search costGPU hours: 15,000 -> 2.3Improved
add Faster AA policy instead of no augmentation policyResNet-50 · ImageNet top-1test error (%): 24.1 -> 23.5Improved
add Faster AA policy instead of CutoutWideResNet-28-10 · Reduced CIFAR-10test error (%): 22.5 -> 14.8Improved
train policy on target CIFAR-100 instead of CIFAR-10 (ablation)Faster AA WideResNet-28-10 · CIFAR-100test error (%): 17.8 -> 17.3Improved
increase number of sub-policies L (ablation)Faster AA WideResNet-40-2 · CIFAR-10test error (%)Improved
increase operation count K per sub-policy from 1 to 4 (ablation)Faster AA WideResNet-40-2 · CIFAR-10test error (%)Improved
train policy on full 50,000 CIFAR-10 images instead of 4,000, with L=10 (ablation)Faster AA WideResNet-40-2 · CIFAR-10test error (%): 3.7 -> 4.1Hurt
train policy with L=80 sub-policies on full CIFAR-10 instead of L=10 (ablation)Faster AA WideResNet-40-2 · CIFAR-10test error (%): 4.1 -> 3.8Improved
add trained policy instead of randomly initialized policy (ablation)Faster AA WideResNet-28-10 · CIFAR-10test error (%): 2.7 -> 2.6Improved

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