AI Paper Atlas

Research map / Image generation / GANs

Attribute Manipulation Generative Adversarial Networks for Fashion Images

Kenan E. Ak, Joo Hwee Lim, Jo Yew Tham, Ashraf A. Kassim

ICCV 2019 · Image generation › GANs · approach: Large-scale GAN latent analysis · 87 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 DC network (ablation)AMGAN · DeepFashionattribute classification accuracy (avg): 74.05 -> 79.48Improved
add DC network (ablation)AMGAN · Shopping100kattribute classification accuracy (avg): 43.15 -> 49.49Improved
add perceptual loss (on top of DC removed) (ablation)AMGAN · DeepFashionattribute classification accuracy (avg): 69.84 -> 74.05Improved
add perceptual loss (on top of DC removed) (ablation)AMGAN · Shopping100kattribute classification accuracy (avg): 35.47 -> 43.15Improved
add attention loss (ablation)AMGAN · DeepFashionattribute classification accuracy (avg): 67.34 -> 69.84Improved
add attention loss (ablation)AMGAN · Shopping100kattribute classification accuracy (avg): 25.50 -> 35.47Improved
use attention loss with CAMs instead of using CAMs directly as attention mask (ablation)AMGAN · DeepFashionattribute classification accuracy (avg): 62.88 -> 69.84Improved
use attention loss with CAMs instead of using CAMs directly as attention mask (ablation)AMGAN · Shopping100kattribute classification accuracy (avg): 26.13 -> 35.47Improved
use AMGAN instead of attention-based Ganimation or SaGANGanimation · Shopping100kattribute classification accuracy (avg): 23.02 -> 49.49Improved
add attention mechanism (Ganimation) to StarGANStarGAN · Shopping100kattribute classification accuracy (avg): 35.76 -> 23.02Hurt
use AMGAN instead of StarGANStarGAN · DeepFashionTop-30 retrieval accuracy (avg): 0.568 -> 0.657Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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