AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

Direct Differentiable Augmentation Search

Aoming Liu, Zehao Huang, Zhiwu Huang, Naiyan Wang

ICCV 2021 · Architectures and efficiency › Neural architecture search · approach: AutoML pipeline search · 44 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
learn p_tp adaptively instead of fixing it to 1.0 (ablation)DDAS · CIFAR-100 (WRN-28-10)test error (%): 24.7 -> 16.6Improved
learn p_tp adaptively instead of fixing it to 1.0 (ablation)DDAS · ImageNet (ResNet-50)test error (%): 23.1 -> 22.3Improved
learn p_tp adaptively instead of best fixed value (ablation)DDAS · CIFAR-100 (WRN-28-10)test error (%): 16.6 vs 16.6No clear effect
learn p_tp adaptively instead of fixed 0.4 (ablation)DDAS · ImageNet (ResNet-50)test error (%): 22.2 -> 22.3Hurt
use dynamic epoch-wise policy instead of fixing p_tp and p_o (ablation)DDAS · CIFAR-100 (WRN-28-10)test error (%): 16.9 -> 16.6Improved
use dynamic epoch-wise policy instead of fixing p_tp and p_o (ablation)DDAS · ImageNet (ResNet-50)test error (%): 22.4 -> 22.3Hurt
use dynamic policy instead of fixing only p_o (ablation)DDAS · ImageNet (ResNet-50)test error (%): 22.2 -> 22.3Hurt
increase sampled policies per step L-hat from 3 to 11 (ablation)DDAS · CIFAR-100 (WRN-28-10)test error (%): 16.6 -> 17.1Hurt
increase sampled policies per step L-hat from 3 to 7 (ablation)DDAS · CIFAR-100 (WRN-28-10)test error (%): 16.6 -> 16.8Hurt
DDAS instead of Faster AA / DADA on CIFAR-100DDAS · CIFAR-100 (WRN-28-10)test error (%): 17.3 -> 16.6 (Faster AA), 17.5 -> 16.6 (DADA)Improved
DDAS instead of AA search for detectionDDAS · COCO (RetinaNet R50)mAP: 38.4 -> 38.1 mAP with 19800 -> 20 search hoursMixed
DDAS augmentation vs baselineRetinaNet R50 · COCO valmAP: 36.9 -> 38.1Improved

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