Research map / Label-efficient and robust learning / Recognition and long-tail
DeepFRC: An End-to-End Deep Learning Model for Functional Registration and Classification
Siyuan Jiang, Yihan Hu, Wenjie Li, Pengcheng Zeng
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 |
|---|---|---|---|
| add neural deformation operator (registration) (ablation) | DeepFRC · Yoga | classification accuracy: 83.1% -> 89.8% | Improved |
| add neural deformation operator (registration) (ablation) | DeepFRC · Symbol (2 classes) | classification accuracy: 91.0% -> 96.0% | Improved |
| add neural deformation operator (registration) (ablation) | DeepFRC · MotionSense | classification accuracy: 90.0% -> 95.0% | Improved |
| add neural deformation operator (registration) (ablation) | DeepFRC · Wave | classification accuracy: 94.4% -> 96.4% | Improved |
| add spectral representation (Fourier basis) (ablation) | DeepFRC · Symbol (3 classes) | classification accuracy: 93.3% -> 96.3% | Improved |
| add spectral representation (Fourier basis) (ablation) | DeepFRC · MotionSense | ATV (registration): 28.8 -> 25.0 | Improved |
| add spectral representation (Fourier basis) (ablation) | DeepFRC · Yoga | classification accuracy: 89.2% -> 89.8% | Improved |
| add classifier network (joint training with label-aware loss) (ablation) | DeepFRC · Yoga | ATV (registration): 136.0 -> 16.2 | Improved |
| use joint DeepFRC instead of TTN | TTN · Yoga | ATV (registration): 57.7 -> 16.2 | Improved |
| use joint DeepFRC instead of TTN | TTN · Yoga | classification accuracy: 89.4% -> 89.8% | No clear effect |
| use DeepFRC instead of SrvfRegNet+TSLANet | SrvfRegNet+TSLANet · Wave | classification accuracy: 96.4% -> 96.4% | No clear effect |
| use DeepFRC instead of SrvfRegNet+TSLANet | SrvfRegNet+TSLANet · Symbol (3 classes) | classification accuracy: 96.3% -> 96.3% | No clear effect |
Closest papers by meaning
- NeuralFLoC: Neural Flow-Based Joint Registration and Clustering of Functional Data (ICML 2026 · similarity 0.89)
- DiffuMatch: Category-Agnostic Spectral Diffusion Priors for Robust Non-rigid Shape Matching (ICCV 2025 · similarity 0.85)
- Metric Learning for Image Registration (CVPR 2019 · similarity 0.85)
- Memory-Scalable and Simplified Functional Map Learning (CVPR 2024 · similarity 0.84)
- Latent Functional Maps: a spectral framework for representation alignment (NeurIPS 2024 · similarity 0.84)
- CARL: A Framework for Equivariant Image Registration (CVPR 2025 · 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.
