Research map / Architectures and efficiency / Neural architecture search
Memory-Augmented Attribute Manipulation Networks for Interactive Fashion Search
Check 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 the memory block for prototype attribute representations (ablation) | AMNet · DARN, one-attribute manipulation | Top-20 retrieval accuracy: 0.230 -> 0.545 | Helped |
| add the memory block for prototype attribute representations (ablation) | AMNet · DeepFashion, one-attribute manipulation | Top-20 retrieval accuracy: 0.208 -> 0.338 | Helped |
| add the triplet ranking loss (ablation) | AMNet · DARN, one-attribute manipulation | Top-20 retrieval accuracy: 0.316 -> 0.545 | Helped |
| add the triplet ranking loss (ablation) | AMNet · DeepFashion, one-attribute manipulation | Top-20 retrieval accuracy: 0.266 -> 0.338 | Helped |
| add the memory block for prototype attribute representations (ablation) | AMNet · DARN, one-attribute manipulation | NDCG@20: 0.23 -> 0.46 | Helped |
| add the memory block for prototype attribute representations (ablation) | AMNet · DeepFashion, one-attribute manipulation | NDCG@20: 0.23 -> 0.39 | Helped |
| add the triplet ranking loss (ablation) | AMNet · DARN, one-attribute manipulation | NDCG@20: 0.32 -> 0.46 | Helped |
| add the triplet ranking loss (ablation) | AMNet · DeepFashion, one-attribute manipulation | NDCG@20: 0.28 -> 0.39 | Helped |
| use AMNet instead of attribute-based retrieval | fashion image retrieval · DARN, one-attribute manipulation | Top-20 retrieval accuracy: 0.340 -> 0.545 | Helped |
| use AMNet instead of attribute-based retrieval | fashion image retrieval · DeepFashion, one-attribute manipulation | Top-20 retrieval accuracy: 0.185 -> 0.338 | Helped |
Closest papers by meaning
- Learning Attribute Representations With Localization for Flexible Fashion Search (CVPR 2018 · similarity 0.90)
- Fashion Microscope: Pixel-Level Attribute Perception via Optimal Transport and Neural Semantic Aggregation (AAAI 2026 · similarity 0.88)
- Learning Attribute and Class-Specific Representation Duet for Fine-Grained Fashion Analysis (CVPR 2023 · similarity 0.86)
- FashionERN: Enhance-and-Refine Network for Composed Fashion Image Retrieval (AAAI 2024 · similarity 0.86)
- Easy Regional Contrastive Learning of Expressive Fashion Representations (NeurIPS 2024 · similarity 0.84)
- Highlighting What Matters: Promptable Embeddings for Attribute-Focused Image Retrieval (NeurIPS 2025 · similarity 0.83)
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.