AI Paper Atlas

Research map / Image generation / GANs

Masked Auto-Encoders Meet Generative Adversarial Networks and Beyond

Zhengcong Fei, Mingyuan Fan, Li Zhu, Junshi Huang, Xiaoming Wei, Xiaolin Wei

CVPR 2023 · Image generation › GANs · approach: Stabilized GAN training · 22 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 a discriminator trained to classify real versus synthesized patchesMAE pretraining with ViT-B · ImageNet-1K fine-tuningtop-1 accuracy: 83.6 -> 84.6Improved
Share generator and discriminator backbone parameters (ablation)GAN-MAE · ImageNet-1K fine-tuning, 800 epochstop-1 accuracy: 83.9 -> 84.3Improved
Share generator and discriminator backbone parameters (ablation)GAN-MAE · ImageNet-1K fine-tuning, 1600 epochstop-1 accuracy: 84.4 -> 84.6Improved
Use adversarial generator training instead of two-stage training (ablation)GAN-MAE · ImageNet-1K fine-tuning, 300 epochstop-1 accuracy: 82.0 -> 82.2Improved
Use adversarial training instead of combined training (ablation)GAN-MAE · ImageNet-1K fine-tuning, 800 epochstop-1 accuracy: 84.1 -> 84.3Improved
Use combined training rather than adversarial training (ablation)GAN-MAE · pretraining compute at 800 epochsGPU time: 317.5h -> 240.5hImproved
Use 70% rather than 75% masking (ablation)GAN-MAE · ImageNet-1K fine-tuning, 800 epochstop-1 accuracy: 84.3 -> 84.3No clear effect
Use 80% rather than 75% masking (ablation)GAN-MAE · ImageNet-1K fine-tuning, 800 epochstop-1 accuracy: 84.3 -> 84.0Hurt
Use 70% rather than 75% masking (ablation)GAN-MAE · ImageNet-1K fine-tuning, 1600 epochstop-1 accuracy: 84.6 -> 84.5Hurt
Use 80% rather than 75% masking (ablation)GAN-MAE · ImageNet-1K fine-tuning, 1600 epochstop-1 accuracy: 84.6 -> 84.4Hurt
Add an image-level contrastive objective to patch discrimination (ablation)GAN-MAE · ImageNet-1K classificationtop-1 accuracyNo clear effect
Use GAN-MAE rather than MAE pretrainingViT-B · ADE20K semantic segmentationmIoU: 47.6 -> 49.5Improved

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