AI Paper Atlas

Research map / Image generation / GANs

Separating Content from Style Using Adversarial Learning for Recognizing Text in the Wild

Canjie Luo, Qingxiang Lin, Yuliang Liu, Lianwen Jin, Chunhua Shen

IJCV 2021 · Image generation › GANs · approach: GAN-based image manipulation · 41 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
generate clean images (separate content from background) as recognizer inputattention recognizer · CUTEword accuracy (%): 74.3 -> 80.9Improved
generate clean images as recognizer inputattention recognizer · regular text (IIIT5K, SVT, IC03, IC13)word accuracy (%): 92.2 -> 92.5 on IIIT5K, 94.0 -> 95.0 on IC03Improved
add style adversarial loss L_s (ablation)content-supervised GAN · SVT-Pword accuracy (%): 71.9 -> 75.0Improved
add style adversarial loss L_s (ablation)content-supervised GAN · IC15word accuracy (%): 65.5 -> 72.5Improved
add content classifier (content supervision) (ablation)style-only GAN · SVT-P, CUTE, IC15word accuracy (%): Failed -> 75.0, 78.4, 72.5Improved
add feedback mechanism (supervise content classifier with recognizer predictions) (ablation)GAN with L_s and L_c · SVT-Pword accuracy (%): 75.0 -> 79.2Improved
add feedback mechanism (ablation)GAN with L_s and L_c · IC15word accuracy (%): 72.5 -> 73.0Improved
replace OTSU binarization with learned GAN separationtext normalization · SVT-Pword accuracy (%): 46.5 -> 79.2Improved
replace word-level CycleGAN with character-level adversarial generationtext normalization · SVT-Pword accuracy (%): 14.6 -> 79.2Improved
integrate method into ASTERASTER · CUTEword accuracy (%): 79.9 -> 85.1Improved
integrate method into ESIRESIR · CUTEword accuracy (%): 83.7 -> 87.8Improved
ensemble source and generated image predictions by confidence (Com.)ASTER + Ours · CUTEword accuracy (%): 85.1 -> 89.6Improved

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