Research map / Graph learning / Graph self-supervised learning
Interpreting CNN Knowledge via an Explanatory Graph
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 explanatory-graph patterns for multi-shot part localization instead of supervised-AOG patterns | VGG-16 part-localization pipeline · CUB200-2011 | normalized distance: 0.0915 -> 0.0862 | Helped |
| Use the explanatory graph instead of fc7+linearSVM | VGG-16 part-localization pipeline · Pascal VOC Part | normalized distance: 0.244 -> 0.177 | Helped |
| Use the explanatory graph instead of fc7+linearSVM | VGG-16 part-localization pipeline · ILSVRC 2013 DET Animal-Part | normalized distance: 0.184 -> 0.125 | Helped |
| Use explanatory-graph patterns rather than raw filter responses | ResNet-50 · CUB200-2011 | location instability: 0.1328 -> 0.0848 | Helped |
| Use explanatory-graph patterns rather than raw filter responses | ResNet-152 · CUB200-2011 | location instability: 0.1346 -> 0.0858 | Helped |
| Use explanatory-graph patterns rather than raw filter responses | VGG-16 · CUB200-2011 | location instability: 0.1398 -> 0.0638 | Helped |
| Use explanatory-graph patterns rather than raw filter responses | VAE-GAN · CUB200-2011 | location instability: 0.1944 -> 0.1066 | Helped |
Closest papers by meaning
- Growing Interpretable Part Graphs on ConvNets via Multi-Shot Learning (AAAI 2017 · similarity 0.91)
- Classification by Attention: Scene Graph Classification with Prior Knowledge (AAAI 2021 · similarity 0.87)
- Distilling Knowledge From Graph Convolutional Networks (CVPR 2020 · similarity 0.87)
- Beyond Grids: Learning Graph Representations for Visual Recognition (NeurIPS 2018 · similarity 0.86)
- Multi-Part Object Representations via Graph Structures and Co-Part Discovery (NeurIPS 2026 · similarity 0.85)
- Object-Centric Representation Learning for Enhanced 3D Semantic Scene Graph Prediction (NeurIPS 2025 · 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.