Research map / Label-efficient and robust learning / Recognition and long-tail
Predictive Inference with Feature Conformal Prediction
Jiaye Teng, Chuan Wen, Dinghuai Zhang, Yoshua Bengio, Yang Gao, Yang Yuan
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 |
|---|---|---|---|
| Feature CP (feature-space conformal prediction) instead of vanilla CP in output space | Synthetic multi-dimensional regression · Synthetic multi-dim regression (alpha=0.1) | band length: 0.401 -> 0.373 | Improved |
| Feature CP instead of vanilla CP in output space | Cityscapes segmentation · Cityscapes segmentation (alpha=0.1) | band length: 40.15 -> 1.032 | Improved |
| Feature CP instead of vanilla CP in output space | Synthetic multi-dimensional regression · Synthetic multi-dim regression (alpha=0.1) | coverage: 89.91 -> 90.13 | No clear effect |
| Feature CP instead of vanilla CP in output space | Cityscapes segmentation · Cityscapes segmentation (alpha=0.1) | coverage: 91.41 -> 90.77 | Mixed |
| Feature CP applied to pretrained ImageNet classifiers (vs RAPS/APS) | ImageNet classification, ResNet 18/50/101, ResNeXt 101, VGG 16 · ImageNet (alpha=0.1) | average set length: e.g., ResNet 18 4.43 -> 3.82 vs RAPS | Improved |
| Feature CP applied to ShuffleNet on ImageNet | ShuffleNet · ImageNet (alpha=0.1) | average set length: 5.05 (RAPS) vs 5.06 (Feature CP) | No clear effect |
| Random (unlearned) network features used for Feature CP instead of trained semantic features (ablation) | Feature CP · Feature CP vs vanilla CP with same network | band length | No clear effect |
| Feature CQR (feature-level version of CQR) instead of CQR | CQR on UCI and other 1-D regression datasets · 1-D regression benchmarks (alpha=0.1) | interval length | Improved |
| Splitting point choice for feature layer (ablation) | Feature CP on small and large networks · Coverage robustness | coverage | No clear effect |
Closest papers by meaning
- Scaling Full Conformal Image Classifiers (NeurIPS 2026 · similarity 0.88)
- Conformal Prediction for Zero-Shot Models (CVPR 2025 · similarity 0.87)
- Conformal Prediction with Learned Features (ICML 2024 · similarity 0.86)
- Self-Calibrating Conformal Prediction (NeurIPS 2024 · similarity 0.85)
- CONTRA: Conformal Prediction Region via Normalizing Flow Transformation (ICLR 2025 · similarity 0.85)
- On Temperature Scaling and Conformal Prediction of Deep Classifiers (ICML 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.
