Research map / Label-efficient and robust learning / Recognition and long-tail
Learning Attribute Representations With Localization for Flexible Fashion Search
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 attribute localization with AAMs and ROI pooling (ablation) | FashionSearchNet · Shopping100k, query + attribute manipulation | Top-30 retrieval accuracy: 5.4% higher than the nearest competitor | Helped |
| Add attribute localization with AAMs and ROI pooling (ablation) | FashionSearchNet · DeepFashion, query + attribute manipulation | Top-30 retrieval accuracy: 6.3% higher than the nearest competitor | Helped |
| Use FashionSearchNet instead of AMNet | Shopping100k, query + attribute manipulation · Shopping100k | Top-30 retrieval accuracy: 16% better than AMNet | Helped |
| Use FashionSearchNet instead of AMNet | DeepFashion, query + attribute manipulation · DeepFashion | Top-30 retrieval accuracy: 13% better than AMNet | Helped |
| Add region awareness and region-specific attribute representations | FashionSearchNet · Shopping100k, region-specific color manipulation user study | Success rate: 8.6% -> 22.2% | Helped |
| Use FashionSearchNet instead of AMNet | Shopping100k, region-specific color manipulation user study · Shopping100k | Success rate: 1.2% -> 8.6% | Helped |
Closest papers by meaning
- Memory-Augmented Attribute Manipulation Networks for Interactive Fashion Search (CVPR 2017 · similarity 0.90)
- Fashion Microscope: Pixel-Level Attribute Perception via Optimal Transport and Neural Semantic Aggregation (AAAI 2026 · similarity 0.87)
- FashionERN: Enhance-and-Refine Network for Composed Fashion Image Retrieval (AAAI 2024 · similarity 0.84)
- Easy Regional Contrastive Learning of Expressive Fashion Representations (NeurIPS 2024 · similarity 0.84)
- TexFit: Text-Driven Fashion Image Editing with Diffusion Models (AAAI 2024 · similarity 0.83)
- AnyDressing: Customizable Multi-Garment Virtual Dressing via Latent Diffusion Models (CVPR 2025 · similarity 0.82)
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.