Research map / Label-efficient and robust learning / Recognition and long-tail
Fine-Grained Fashion Similarity Learning by Attribute-Specific Embedding Network
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 |
|---|---|---|---|
| learn attribute-specific embeddings with ASA and ACA rather than use CSN's fixed attribute mask | ASEN · FashionAI | MAP: 53.52 -> 61.02 | Helped |
| learn attribute-specific embeddings with ASA and ACA rather than use CSN's fixed attribute mask | ASEN · DARN | MAP: 50.86 -> 53.31 | Helped |
| learn attribute-specific embeddings with ASA and ACA rather than use CSN's fixed attribute mask | ASEN · DeepFashion | MAP: 8.01 -> 8.74 | Helped |
| learn attribute-specific embeddings with ASA and ACA rather than use CSN's fixed attribute mask | ASEN · Zappos50k | Prediction Accuracy(%): 89.27 -> 90.79 | Helped |
| add attribute-aware spatial attention instead of mean pooling (ablation) | ASEN · FashionAI | MAP: 56.35 -> 61.02 | Helped |
| add attribute-aware channel attention (ablation) | ASEN · FashionAI | MAP: 50.87 -> 61.02 | Helped |
| add attribute-aware spatial attention instead of mean pooling (ablation) | ASEN · DARN | MAP: 51.39 -> 53.31 | Helped |
| add attribute-aware channel attention (ablation) | ASEN · DARN | MAP: 48.02 -> 53.31 | Helped |
| add attribute-aware spatial attention instead of mean pooling (ablation) | ASEN · DeepFashion | MAP: 8.41 -> 8.74 | Helped |
| add attribute-aware channel attention (ablation) | ASEN · DeepFashion | MAP: 8.32 -> 8.74 | Helped |
| add attribute-aware spatial attention instead of mean pooling (ablation) | ASEN · Zappos50k | Prediction Accuracy(%): 90.18 -> 90.79 | Helped |
| add attribute-aware channel attention (ablation) | ASEN · Zappos50k | Prediction Accuracy(%): 89.01 -> 90.79 | Helped |
Closest papers by meaning
- Learning Attribute and Class-Specific Representation Duet for Fine-Grained Fashion Analysis (CVPR 2023 · similarity 0.92)
- Fashion Microscope: Pixel-Level Attribute Perception via Optimal Transport and Neural Semantic Aggregation (AAAI 2026 · similarity 0.86)
- TransNFCM: Translation-Based Neural Fashion Compatibility Modeling (AAAI 2019 · similarity 0.86)
- Learning Attribute Representations With Localization for Flexible Fashion Search (CVPR 2018 · similarity 0.86)
- FashionERN: Enhance-and-Refine Network for Composed Fashion Image Retrieval (AAAI 2024 · similarity 0.85)
- Easy Regional Contrastive Learning of Expressive Fashion Representations (NeurIPS 2024 · 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.