AI Paper Atlas

Research map / Image generation / GANs

Adaptive Feature Interpolation for Low-Shot Image Generation

Mengyu Dai, Haibin Hang, Xiaoyang Guo

ECCV 2022 · Image generation › GANs · approach: GAN-based image manipulation · 13 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 adaptive feature interpolation (AFI) to FastGANFastGAN · Shells (1024x1024)FID: 152.53 -> 124.80Improved
add AFI to StyleGAN2 hinge loss with n=20 output neuronsStyleGAN2 · Shells (1024x1024)FID: 101.72 -> 62.99Improved
add AFI to StyleGAN2 hinge loss with n=20 output neuronsStyleGAN2 · Art (1024x1024)FID: 58.42 -> 43.94Improved
use multidimensional discriminator output (n=20) in StyleGAN2 without feature interpolation (ablation)StyleGAN2 · Shells (1024x1024)FID: 123.66 -> 101.72Improved
add AFI to CIFAR-10 baseline with 100 training imagesCIFAR-10 baseline · CIFAR-10 (100 images)FID: 42.80 -> 27.62Improved
add AFI to CIFAR-10 baseline with 1% training dataCIFAR-10 baseline · CIFAR-10 (1% data)FID: 19.69 -> 13.50Improved
mixup-style feature interpolation instead of AFI (ablation)StyleGAN2 (no transformation augmentation) · ShellsFID: 229.83 -> 319.80Hurt
input-space mixup instead of AFI (ablation)StyleGAN2 (no transformation augmentation) · ShellsFID: 229.83 -> 135.66Improved
use skewed Dirichlet weights (t=1) instead of uniform (t=0) for neighbor interpolation (ablation)FastGAN + feature interpolation · Shells (k=2)FID: 140.89 -> 130.98Improved
interpolate features with k=2 neighbors instead of no interpolation (k=1), uniform weights (ablation)FastGAN + feature interpolation · ShellsFID: 165.72 -> 140.89Improved
use feature interpolation instead of image interpolation (mixup) in StyleGAN2 training (ablation)StyleGAN2 · Shells (FID during training)training stabilityImproved
add AFI to StyleGAN2 hinge n=20 on Dog 256x256 vs Grumpy catStyleGAN2 · Dog (256x256)FID: 56.43 -> 49.14Improved

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