AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

RD-GAN: Few/Zero-Shot Chinese Character Style Transfer via Radical Decomposition and Rendering

Yaoxiong Huang, Mengchao He, Lianwen Jin, Yongpan Wang

ECCV 2020 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Transductive and semantic-dictionary zero-shot · 72 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
augment real training data with RD-GAN generated characterscharacter classifier · TKH recognition (D1)accuracy (%): 82.45 -> 88.11Improved
use RD-GAN generated data instead of EMD generated datacharacter classifier · TKH recognition (D1)accuracy (%): 87.21 -> 88.11Improved
use RD-GAN generated data instead of zi2zi generated datacharacter classifier · TKH recognition (D1)accuracy (%): 85.63 -> 88.11Improved
add pix2pix generated datacharacter classifier · TKH recognition (D1)accuracy (%): 82.45 -> 84.74Improved
add synthtext2014 generated datacharacter classifier · TKH recognition (D1)accuracy (%): 82.45 -> 83.25Improved
train RD-GAN with 5 samples per class instead of 50 (D2 vs D1)RD-GAN · TKHSSIM: 0.9647 -> 0.9642No clear effect
train RD-GAN with 5 samples per class instead of 50 (D2 vs D1)RD-GAN · TKHL1 loss: 0.0088 -> 0.0089No clear effect
decompose characters into radicals to reach few-shot/zero-shot generalizationRD-GAN vs MC-GAN · TKH zero-shot (D3)SSIM: 0.8633 -> 0.9112Improved
add lateral connections to the radical rendering module (ablation)RD-GAN · TKH (Fig. 6 ablation)L1 lossImproved
add multi-level discriminator instead of single-level (ablation)RD-GAN · TKH (Fig. 6 ablation)SSIMImproved
add additional losses (L2, total variation, content) (ablation)RD-GAN · TKH (Fig. 6 ablation)L1 loss / RMSE / SSIMImproved

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