Research map / Detection and segmentation / Open-set and few-shot detection
Human-Like Sketch Object Recognition via Analogical Learning
Kezhen Chen, Irina Rabkina, Matthew D. McLure, Kenneth D. Forbus
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 |
|---|---|---|---|
| increase training examples per digit from 10 to 100 | CogSketch + SAGE · MNIST test (10k) | accuracy: 54.9% -> 76.24% | Improved |
| increase training examples per digit from 100 to 500 | CogSketch + SAGE · MNIST test (10k) | accuracy: 76.24% -> 85.03% | Improved |
| use analogical generalization over relational sketch representations instead of LeNet-5 CNN with 9 training examples per class | Coloring Book Objects classifier · Coloring Book Objects (leave-one-out) | accuracy: 5.26% -> 29.47% | Improved |
Closest papers by meaning
- Visual Relation Detection using Hybrid Analogical Learning (AAAI 2021 · similarity 0.86)
- Action Recognition From Skeleton Data via Analogical Generalization Over Qualitative Representations (AAAI 2018 · similarity 0.85)
- Learning Dense Correspondences between Photos and Sketches (ICML 2023 · similarity 0.85)
- Learning to Learn Image Classifiers With Visual Analogy (CVPR 2019 · similarity 0.85)
- SketchEmbedNet: Learning Novel Concepts by Imitating Drawings (ICML 2021 · similarity 0.85)
- Enhance Sketch Recognition’s Explainability via Semantic Component-Level Parsing (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.
