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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add DC network (ablation) | AMGAN · DeepFashion | attribute classification accuracy (avg): 74.05 -> 79.48 | Improved |
| add DC network (ablation) | AMGAN · Shopping100k | attribute classification accuracy (avg): 43.15 -> 49.49 | Improved |
| add perceptual loss (on top of DC removed) (ablation) | AMGAN · DeepFashion | attribute classification accuracy (avg): 69.84 -> 74.05 | Improved |
| add perceptual loss (on top of DC removed) (ablation) | AMGAN · Shopping100k | attribute classification accuracy (avg): 35.47 -> 43.15 | Improved |
| add attention loss (ablation) | AMGAN · DeepFashion | attribute classification accuracy (avg): 67.34 -> 69.84 | Improved |
| add attention loss (ablation) | AMGAN · Shopping100k | attribute classification accuracy (avg): 25.50 -> 35.47 | Improved |
| use attention loss with CAMs instead of using CAMs directly as attention mask (ablation) | AMGAN · DeepFashion | attribute classification accuracy (avg): 62.88 -> 69.84 | Improved |
| use attention loss with CAMs instead of using CAMs directly as attention mask (ablation) | AMGAN · Shopping100k | attribute classification accuracy (avg): 26.13 -> 35.47 | Improved |
| use AMGAN instead of attention-based Ganimation or SaGAN | Ganimation · Shopping100k | attribute classification accuracy (avg): 23.02 -> 49.49 | Improved |
| add attention mechanism (Ganimation) to StarGAN | StarGAN · Shopping100k | attribute classification accuracy (avg): 35.76 -> 23.02 | Hurt |
| use AMGAN instead of StarGAN | StarGAN · DeepFashion | Top-30 retrieval accuracy (avg): 0.568 -> 0.657 | Improved |
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.
- StarGAN — StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation (CVPR 2018) · better on 8 of 8 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
- Generative Attribute Controller With Conditional Filtered Generative Adversarial Networks (CVPR 2017 · similarity 0.88)
- Fashion Editing With Adversarial Parsing Learning (CVPR 2020 · similarity 0.88)
- Generative Adversarial Network with Spatial Attention for Face Attribute Editing (ECCV 2018 · similarity 0.88)
- ManiGAN: Text-Guided Image Manipulation (CVPR 2020 · similarity 0.87)
- An Adversarial Framework for Generating Unseen Images by Activation Maximization (AAAI 2022 · similarity 0.87)
- Memory-Augmented Attribute Manipulation Networks for Interactive Fashion Search (CVPR 2017 · similarity 0.87)
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.
