Research map / Graph learning / Knowledge and temporal graphs
Layout-Graph Reasoning for Fashion Landmark Detection
Weijiang Yu, Xiaodan Liang, Ke Gong, Chenhan Jiang, Nong Xiao, Liang Lin
Check 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 hierarchical layout-graph reasoning with four stacked LGR layers | VGG16 · FLD | Avg. NE: .0871 -> .0419 | Improved |
| add hierarchical layout-graph reasoning with four stacked LGR layers | VGG16 · DeepFashion | Avg. NE: .0484 -> .0336 | Improved |
| use five instead of four stacked LGR layers (ablation) | LGR · FLD | Avg. NE: .0419 -> .0405 | Improved |
| replace LGR clustering/deconvolution with one normal graph layer (ablation) | VGG16 on FLD · FLD | Avg. NE: .0419 -> .0531 | Hurt |
| replace LGR clustering/deconvolution with normal graph layers (ablation) | VGG16 on DeepFashion · DeepFashion | Avg. NE: .0336 -> .0437 | Hurt |
| increase normal graph depth from two to eight layers (ablation) | normal graph model on FLD · FLD | Avg. NE: .0471 -> .0954 | Hurt |
| increase normal graph depth from two to eight layers (ablation) | normal graph model on DeepFashion · DeepFashion | Avg. NE: .0437 -> .0779 | Hurt |
| use three instead of one graph clustering/deconvolution operation (ablation) | LGR · FLD | Avg. NE: .0488 -> .0419 | Improved |
| use three instead of one graph clustering/deconvolution operation (ablation) | LGR · DeepFashion | Avg. NE: .0403 -> .0336 | Improved |
| inject four stacked LGR layers before ConvBlock5 rather than ConvBlock3 (ablation) | VGG16 on FLD · FLD | Avg. NE: .0574 -> .0419 | Improved |
| inject four stacked LGR layers before ConvBlock5 rather than ConvBlock1 (ablation) | VGG16 on FLD · FLD | Avg. NE: .0811 -> .0419 | Improved |
| add hierarchical layout-graph reasoning | VGG16 · FFLD test | Avg. NE: .1272 -> .1180 | Improved |
Closest papers by meaning
- Fashion Landmark Detection in the Wild (ECCV 2016 · similarity 0.91)
- Attentive Fashion Grammar Network for Fashion Landmark Detection and Clothing Category Classification (CVPR 2018 · similarity 0.87)
- Texture and Shape Biased Two-Stream Networks for Clothing Classification and Attribute Recognition (CVPR 2020 · similarity 0.87)
- Fashion Retrieval via Graph Reasoning Networks on a Similarity Pyramid (ICCV 2019 · similarity 0.87)
- DeepFashion2: A Versatile Benchmark for Detection, Pose Estimation, Segmentation and Re-Identification of Clothing Images (CVPR 2019 · similarity 0.86)
- FashionTailor: Controllable Clothing Editing for Human Images with Appearance Preserving (AAAI 2025 · 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.
