AI Paper Atlas

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

Implicit Semantic Data Augmentation for Deep Networks

Yulin Wang, Xuran Pan, Shiji Song, Hong Zhang, Gao Huang, Cheng Wu

NeurIPS 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Loss design and classifier theory · 57 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 ISDAResNet-50 · ImageNet valTop-1 error rate: 23.0 -> 21.9Improved
Add ISDAResNet-101 · ImageNet valTop-1 error rate: 21.7 -> 20.8Improved
Add ISDADenseNet-BC-121 · ImageNet valTop-1 error rate: 23.7 -> 23.2Improved
Add ISDAResNet-110 · CIFAR-10error rate: 6.76 ± 0.34% -> 6.33 ± 0.19%Improved
Add ISDAResNet-110 · CIFAR-100error rate: 28.67 ± 0.44% -> 27.57 ± 0.46%Improved
Add ISDA to AutoAugmentWide-ResNet-28-10 · CIFAR-100error rate: 16.60 ± 0.40% -> 15.62 ± 0.32%Improved
Add ISDA to CutoutWide-ResNet-28-10 · CIFAR-100error rate: 18.05 ± 0.25% -> 17.02 ± 0.11%Improved
Use class-conditional covariance rather than identity covariance (ablation)ISDA · CIFAR-10error rate: 3.63±0.12% -> 3.58±0.15%Improved
Use class-conditional covariance rather than identity covariance (ablation)ISDA · CIFAR-100error rate: 18.53±0.02% -> 17.98±0.15%Improved
Retain covariance correlations instead of using only diagonal entries (ablation)ISDA · CIFAR-10error rate: 3.70±0.15% -> 3.58±0.15%Improved
Retain covariance correlations instead of using only diagonal entries (ablation)ISDA · CIFAR-100error rate: 18.23±0.02% -> 17.98±0.15%Improved
Use class-specific covariance matrices rather than one global covariance (ablation)ISDA · CIFAR-10error rate: 3.67±0.07% -> 3.58±0.15%Improved

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