Research map / Label-efficient and robust learning / Recognition and long-tail
Learning to Generate an Unbiased Scene Graph by Using Attribute-Guided Predicate Features
Lei Wang, Zejian Yuan, Badong Chen
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 balanced predicate-feature training with A-PFG to PFRL (ablation) | PFRL · VG150 PredCls | mR@100: 20.0 -> 44.3 | Improved |
| add balanced predicate-feature training with A-PFG to PFRL (ablation) | PFRL · VG150 SGCls | mR@100: 10.8 -> 25.8 | Improved |
| add balanced predicate-feature training with A-PFG to PFRL (ablation) | PFRL · VG150 SGDet | mR@100: 9.3 -> 21.7 | Improved |
| use predicate-feature generation instead of bi-level image re-sampling (ablation) | PFRL · VG150 SGDet | mR@100: 14.9 -> 21.4 | Improved |
| add subject and object class labels to predicate-label guidance (ablation) | PFRL predicate-feature generator · VG150 PredCls | mR@100: 42.7 -> 43.7 | Improved |
| add subject and object class labels to predicate-label guidance (ablation) | PFRL predicate-feature generator · VG150 SGCls | mR@100: 25.4 -> 25.4 | No clear effect |
| add union visual features to predicate-label guidance (ablation) | PFRL predicate-feature generator · VG150 PredCls | mR@100: 42.7 -> 43.9 | Improved |
| add union visual features to predicate-label guidance (ablation) | PFRL predicate-feature generator · VG150 SGCls | mR@100: 25.4 -> 25.7 | Improved |
| add cross-reconstruction and distribution-alignment losses to the basic VAE loss (ablation) | A-PFG · VG150 PredCls | mR@100: 43.3 -> 44.3 | Improved |
| add cross-reconstruction and distribution-alignment losses to the basic VAE loss (ablation) | A-PFG · VG150 SGDet | mR@100: 21.0 -> 21.7 | Improved |
Closest papers by meaning
- Noise-Guided Predicate Representation Extraction and Diffusion-Enhanced Discretization for Scene Graph Generation (ICML 2025 · similarity 0.91)
- RA-SGG: Retrieval-Augmented Scene Graph Generation Framework via Multi-Prototype Learning (AAAI 2025 · similarity 0.90)
- Leveraging Predicate and Triplet Learning for Scene Graph Generation (CVPR 2024 · similarity 0.89)
- Panoptic Scene Graph Generation with Semantics-Prototype Learning (AAAI 2024 · similarity 0.89)
- Adaptive Self-training Framework for Fine-grained Scene Graph Generation (ICLR 2024 · similarity 0.88)
- Scene Graph-Grounded Image Generation (AAAI 2025 · similarity 0.88)
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.
