Research map / Vision-language and multimodal / Human and embodied modeling
Learning Attribute-Driven Disentangled Representations for Interactive Fashion Retrieval
Yuxin Hou, Eleonora Vig, Michael Donoser, Loris Bazzani
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 consistency loss Lc (ablation) | ADDE-M · Shopping100k attribute manipulation | Top-30 accuracy: 55.39 -> 59.81 | Improved |
| add consistency loss Lc (ablation) | ADDE-M · DeepFashion attribute manipulation | Top-30 accuracy: 30.83 -> 31.52 | Improved |
| add memory block loss Lmem (ablation) | ADDE-M · Shopping100k attribute manipulation | Top-30 accuracy: 58.82 -> 59.81 | Improved |
| add memory block loss Lmem (ablation) | ADDE-M · DeepFashion attribute manipulation | Top-30 accuracy: 31.11 -> 31.52 | Improved |
| add compositional triplet loss Lct (ablation) | ADDE-M · Shopping100k attribute manipulation | Top-30 accuracy: 58.41 -> 59.81 | Improved |
| add compositional triplet loss Lct (ablation) | ADDE-M · DeepFashion attribute manipulation | Top-30 accuracy: 30.15 -> 31.52 | Improved |
| add label triplet loss Llt (ablation) | ADDE-M · Shopping100k attribute manipulation | Top-30 accuracy: 57.74 -> 59.81 | Improved |
| add label triplet loss Llt (ablation) | ADDE-M · DeepFashion attribute manipulation | Top-30 accuracy: 30.99 -> 31.52 | Improved |
| replace AMNet with ADDE-M | attribute manipulation retrieval · Shopping100k | Top-30 accuracy: 42.94 -> 59.81 | Improved |
| replace AMNet with ADDE-M | attribute manipulation retrieval · DeepFashion | Top-30 accuracy: 22.94 -> 31.52 | Improved |
| replace CSN reimplementation with ADDE-C | conditional similarity triplet prediction · Shopping100k | accuracy: 86.07 -> 87.31 | Improved |
| replace CSN reimplementation with ADDE-C subspace selection | conditional similarity retrieval · Zappos50k | MAP@30: 81.60 -> 83.57 | Improved |
Closest papers by meaning
- Memory-Augmented Attribute Manipulation Networks for Interactive Fashion Search (CVPR 2017 · similarity 0.91)
- Learning Attribute and Class-Specific Representation Duet for Fine-Grained Fashion Analysis (CVPR 2023 · similarity 0.89)
- Fashion Microscope: Pixel-Level Attribute Perception via Optimal Transport and Neural Semantic Aggregation (AAAI 2026 · similarity 0.89)
- Learning Attribute Representations With Localization for Flexible Fashion Search (CVPR 2018 · similarity 0.88)
- Easy Regional Contrastive Learning of Expressive Fashion Representations (NeurIPS 2024 · similarity 0.87)
- FashionERN: Enhance-and-Refine Network for Composed Fashion Image Retrieval (AAAI 2024 · 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.
