Research map / Label-efficient and robust learning / Recognition and long-tail
Proximity-Informed Calibration for Deep Neural Networks
Miao Xiong, Ailin Deng, Pang Wei Koh, Jiaying Wu, Shen Li, Jianqing Xu, Bryan Hooi
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 |
|---|---|---|---|
| Apply ProCal directly to model confidence | ResNet50 · iNaturalist 2021 | ECE: 4.85 -> 0.78 | Improved |
| Apply ProCal directly to model confidence | ResNet50 · iNaturalist 2021 | ACE: 4.86 -> 0.76 | Improved |
| Apply ProCal directly to model confidence | ResNet50 · iNaturalist 2021 | MCE: 0.55 -> 0.18 | Improved |
| Apply ProCal directly to model confidence | ResNet50 · iNaturalist 2021 | PIECE: 4.91 -> 1.51 | Improved |
| Apply ProCal directly to model confidence | RoBERTa · Yahoo Answers Topics | ECE: 4.56 -> 0.51 | Improved |
| Apply ProCal directly to model confidence | RoBERTa · Yahoo Answers Topics | ACE: 4.56 -> 0.54 | Improved |
| Apply ProCal directly to model confidence | RoBERTa · Yahoo Answers Topics | MCE: 0.84 -> 0.09 | Improved |
| Apply ProCal directly to model confidence | RoBERTa · Yahoo Answers Topics | PIECE: 4.73 -> 1.32 | Improved |
| Apply ProCal directly to model confidence | RoBERTa · MultiNLI Mismatch | ECE: 2.47 -> 1.45 | Improved |
| Apply ProCal directly to model confidence | RoBERTa · MultiNLI Mismatch | ACE: 2.62 -> 1.46 | Improved |
| Apply ProCal directly to model confidence | RoBERTa · MultiNLI Mismatch | MCE: 0.85 -> 0.37 | Improved |
| Apply ProCal directly to model confidence | RoBERTa · MultiNLI Mismatch | PIECE: 3.54 -> 2.78 | Improved |
Closest papers by meaning
- Rethinking Calibration of Deep Neural Networks: Do Not Be Afraid of Overconfidence (NeurIPS 2021 · similarity 0.87)
- A Benchmark Study on Calibration (ICLR 2024 · similarity 0.87)
- Reassessing How to Compare and Improve the Calibration of Machine Learning Models (ICLR 2025 · similarity 0.85)
- Towards Precise Prediction Uncertainty in GNNs: Refining GNNs with Topology-grouping Strategy (AAAI 2025 · similarity 0.85)
- Uncertainty Weighted Gradients for Model Calibration (CVPR 2025 · similarity 0.85)
- On the Limitations of Temperature Scaling for Distributions with Overlaps (ICLR 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.
