AI Paper Atlas

Research map / Image generation / GANs

Effective Data Augmentation with Multi-Domain Learning GANs

Shin'ya Yamaguchi, Sekitoshi Kanai, Takeharu Eda

AAAI 2020 · Image generation › GANs · approach: Stabilized GAN training · 23 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
Train the GAN jointly on target and outer domains instead of fine-tuning from the outer domainGAN-based data augmentation · CIFAR-100Top-1 accuracy (%): 25.9±0.5 -> 28.9±0.5Improved
Train the GAN jointly on target and outer domains instead of fine-tuning from the outer domainGAN-based data augmentation · FGVC-AircraftTop-1 accuracy (%): 24.1±0.4 -> 27.3±0.9Improved
Train the GAN jointly on target and outer domains instead of fine-tuning from the outer domainGAN-based data augmentation · Indoor Scene RecognitionTop-1 accuracy (%): 24.0±0.2 -> 26.1±0.7Improved
Add conventional data augmentation to DFDF · CIFAR-100Top-1 accuracy (%): 30.7±0.7 -> 32.1±0.7Improved
Add conventional data augmentation to DFDF · FGVC-AircraftTop-1 accuracy (%): 29.6±0.9 -> 31.2±0.7Improved
Add conventional data augmentation to DFDF · Indoor Scene RecognitionTop-1 accuracy (%): 31.0±0.3 -> 32.4±1.7Improved
Add discriminator rejection sampling (DRS) (ablation)DF · CIFAR-100Top-1 accuracy (%): 28.3±0.7 -> 28.9±0.5Improved
Add discriminator rejection sampling (DRS) (ablation)DF · FGVC-AircraftTop-1 accuracy (%): 27.0±0.5 -> 27.3±0.9Improved
Add discriminator rejection sampling (DRS) (ablation)DF · Indoor Scene RecognitionTop-1 accuracy (%): 25.4±0.1 -> 26.1±0.7Improved
Use the relevance-and-diversity outer-dataset metric M and avoid the worst outer dataset (ablation)DF · CIFAR-100Top-1 accuracy (%): 25.5±0.3 -> 28.9±0.5Improved
Use the relevance-and-diversity outer-dataset metric M and avoid the worst outer dataset (ablation)DF · FGVC-AircraftTop-1 accuracy (%): 24.2±0.3 -> 27.3±0.9Improved
Use the relevance-and-diversity outer-dataset metric M and avoid the worst outer dataset (ablation)DF · Indoor Scene RecognitionTop-1 accuracy (%): 24.2±0.3 -> 26.1±0.7Improved

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