Research map / Graph learning / Knowledge and temporal graphs
Fine-Grained Predicates Learning for Scene Graph Generation
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 FGPL to the benchmark model | Motif, VCTree, and Transformer · Visual Genome PredCls | mR@100: 15.8 vs. 37.5; 16.1 vs. 40.2; 17.5 vs. 40.3 | Helped |
| Add Entity Discriminating Loss to CDL (ablation) | Transformer, VCTree, and Motif · Visual Genome PredCls | mR@100: 35.4 -> 40.3; 35.3 -> 40.2; 34.4 -> 37.5 | Helped |
| Use Predicate Correlation in EDL (ablation) | Transformer with EDL · Visual Genome PredCls | mR@50: 17.0 -> 22.0 | Helped |
| Use the Balancing Factor in EDL (ablation) | Transformer with EDL · Visual Genome PredCls | mR@50: 18.9 -> 22.0 | Helped |
| Use both Predicate Correlation and Balancing Factor in EDL (ablation) | Transformer with EDL · Visual Genome PredCls | mR@50: 16.2 -> 22.0 | Helped |
| Use Re-weighting Factor in CDL (ablation) | Transformer with CDL · Visual Genome PredCls | mR@50: 16.0 -> 28.6 | Helped |
| Add Predicate Correlation to CDL (ablation) | Transformer with CDL and Re-weighting Factor · Visual Genome PredCls | mR@50: 28.6 -> 31.4 | Helped |
Closest papers by meaning
- Noise-Guided Predicate Representation Extraction and Diffusion-Enhanced Discretization for Scene Graph Generation (ICML 2025 · similarity 0.90)
- Leveraging Predicate and Triplet Learning for Scene Graph Generation (CVPR 2024 · similarity 0.89)
- RA-SGG: Retrieval-Augmented Scene Graph Generation Framework via Multi-Prototype Learning (AAAI 2025 · similarity 0.87)
- Multi-Prototype Space Learning for Commonsense-Based Scene Graph Generation (AAAI 2024 · similarity 0.87)
- Democratizing Fine-grained Visual Recognition with Large Language Models (ICLR 2024 · similarity 0.87)
- Adaptive Self-training Framework for Fine-grained Scene Graph Generation (ICLR 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.