Research map / Graph learning / Knowledge and temporal graphs
The More You Know: Using Knowledge Graphs for Image Classification
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 the Visual Genome and WordNet graph to GSNN | GSNN on Visual Genome multi-label · Visual Genome multi-label | mAP: 32.83 -> 33 | Helped |
| Use graph reasoning with the Visual Genome graph | VGG+Det baseline on Visual Genome multi-label · Visual Genome multi-label | mAP: 31.4 -> 32.83 | Helped |
| Use graph reasoning with the combined Visual Genome and WordNet graph | VGG+Det baseline on Visual Genome multi-label · Visual Genome multi-label | mAP: 31.4 -> 33 | Helped |
| Use graph reasoning with the Visual Genome graph | VGG+Det baseline on COCO · COCO multi-label | mAP: 73.93 -> 77.57 | Helped |
| Use graph reasoning with the combined Visual Genome and WordNet graph | VGG+Det baseline on COCO · COCO multi-label | mAP: 73.93 -> 75.73 | Helped |
| Add WordNet to the Visual Genome graph | GSNN on COCO · COCO multi-label | mAP: 77.57 -> 75.73 | Hurt |
| Use only even COCO detectors (ablation) | GSNN-VG on COCO · COCO multi-label, even detectors | mAP: 71.87 -> 73 | Helped |
| Use only odd COCO detectors (ablation) | GSNN-VG on COCO · COCO multi-label, odd detectors | mAP: 71.73 -> 73.43 | Helped |
| Use only even COCO detectors (ablation) | GSNN-VG+WN on COCO · COCO multi-label, even detectors | mAP: 71.87 -> 73.59 | Helped |
| Use only odd COCO detectors (ablation) | GSNN-VG+WN on COCO · COCO multi-label, odd detectors | mAP: 71.73 -> 73.97 | Helped |
| Reduce the training set to 1,000 or 500 examples (ablation) | GSNN-based methods versus baselines on Visual Genome · Visual Genome low-data setting | mAP | No clear effect |
Closest papers by meaning
- Classification by Attention: Scene Graph Classification with Prior Knowledge (AAAI 2021 · similarity 0.89)
- Core Knowledge Learning Framework for Graph (AAAI 2025 · similarity 0.85)
- Toward a Unified Statistical Theory of Unsupervised Pretraining and Supervised Neural Knowledge Graph Learning (NeurIPS 2026 · similarity 0.85)
- The Underappreciated Power of Vision Models for Graph Structural Understanding (NeurIPS 2025 · similarity 0.85)
- Graph Classification via Reference Distribution Learning: Theory and Practice (NeurIPS 2024 · similarity 0.84)
- Knowledge-Aware Neuron Interpretation for Scene Classification (AAAI 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.