Research map / Detection and segmentation / Open-set and few-shot detection
Growing Interpretable Part Graphs on ConvNets via Multi-Shot Learning
Read the paperCheck 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 |
|---|---|---|---|
| Use the AOG-based latent-pattern mining method instead of Fast-RCNN | VGG-16 part localization · ILSVRC 2013 DET Animal-Part, 3-shot head | center prediction accuracy: 46.9 -> 83.2 | Helped |
| Use the AOG-based latent-pattern mining method instead of Fast-RCNN | VGG-16 part localization · ILSVRC 2013 DET Animal-Part, 3-shot front legs | center prediction accuracy: 32.3 -> 71.2 | Helped |
| Use the AOG-based latent-pattern mining method instead of Fast-RCNN | VGG-16 part localization · PASCAL VOC Part, 3-shot head | center prediction accuracy: 54.5 -> 75.1 | Helped |
| Use the AOG-based latent-pattern mining method instead of Fast-RCNN | VGG-16 part localization · CUB200-2011, 3-shot head | normalized distance: 0.2333 -> 0.1115 | Helped |
| Increase annotations from 3-shot to 12-shot | AOG part localization · PASCAL VOC Part and ILSVRC 2013 DET Animal-Part | center prediction accuracy: 0.9%--2.9% | Helped |
Closest papers by meaning
- Interpreting CNN Knowledge via an Explanatory Graph (AAAI 2018 · similarity 0.91)
- Beyond Holistic Object Recognition: Enriching Image Understanding With Part States (CVPR 2018 · similarity 0.91)
- Multi-Part Object Representations via Graph Structures and Co-Part Discovery (NeurIPS 2026 · similarity 0.87)
- PartNeXt: A Next-Generation Dataset for Fine-Grained and Hierarchical 3D Part Understanding (NeurIPS 2025 · similarity 0.86)
- Interpretable Image Classification via Non-parametric Part Prototype Learning (CVPR 2025 · similarity 0.86)
- Generative 3D Part Assembly via Part-Whole-Hierarchy Message Passing (CVPR 2024 · similarity 0.85)
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.