Research map / Image generation / Editing and style transfer
Learning to Appreciate the Aesthetic Effects of Clothing
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 correlative-label guidance (categories as reconstruction labels) to the stacked DAE (ablation) | SDAE + SVM · Image-scale space mapping | MSE: 0.3395 -> 0.3256 | Helped |
| stack multiple hidden layers on DAE-GCL (ablation) | DAE-GCL + SVM · Image-scale space mapping | MSE: 0.3365 -> 0.3256 | Helped |
| use categories as correlative labels instead of input features (ablation) | SDAE-GCL + SVM · Image-scale space mapping | MSE: 0.3458 -> 0.3256 | Helped |
| add an autoencoder (DAE) before SVM regression | SVM · Image-scale space mapping | MSE: 0.3578 -> 0.3398 | Helped |
| use KNN instead of SVM as regressor (ablation) | SDAE-GCL · Image-scale space mapping | MSE: 0.3256 -> 0.3807 | Hurt |
| use BLR or DNN instead of SVM as regressor (ablation) | SDAE-GCL · Image-scale space mapping | MSE: 0.3256 -> 0.3271 (BLR), 0.3270 (DNN) | No clear effect |
| use only color features (drop pattern features) (ablation) | SDAE-GCL + SVM · Image-scale space mapping | MSE: 0.3256 -> 0.4212 | Hurt |
| use only pattern features (drop color features) (ablation) | SDAE-GCL + SVM · Image-scale space mapping | MSE: 0.3256 -> 0.5111 | Hurt |
| increase unlabeled data size (ablation) | SDAE-GCL · Image-scale space mapping | MSE | Helped |
| increase hidden layers beyond five (ablation) | SDAE-GCL · Image-scale space mapping | MSE | Hurt |
Closest papers by meaning
- Easy Regional Contrastive Learning of Expressive Fashion Representations (NeurIPS 2024 · similarity 0.86)
- TexFit: Text-Driven Fashion Image Editing with Diffusion Models (AAAI 2024 · similarity 0.85)
- Seeing the Abstract: Translating the Abstract Language for Vision Language Models (CVPR 2025 · similarity 0.85)
- Aligning Vision Models with Human Aesthetics in Retrieval: Benchmarks and Algorithms (NeurIPS 2024 · similarity 0.85)
- AnyDressing: Customizable Multi-Garment Virtual Dressing via Latent Diffusion Models (CVPR 2025 · similarity 0.84)
- Bridging Cognitive Gap: Hierarchical Description Learning for Artistic Image Aesthetics Assessment (AAAI 2026 · similarity 0.84)
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.