paper-with-me

Papers

Bin-wise Temperature Scaling (BTS): Improvement in Confidence Calibration Performance through Simple Scaling Techniques

2019-08-30 · Byeongmoon Ji, Hyemin Jung, Jihyeun Yoon, Kyungyul Kim, Younghak Shin

The prediction reliability of neural networks is important in many applications. Specifically, in safety-critical domains, such as cancer prediction or autonomous driving, a reliable confidence of model's prediction is critical for the interpretation of the results. Modern deep neural networks have achieved a significant improvement in performance for many different image classification tasks. However, these networks tend to be poorly calibrated in terms of output confidence. Temperature scaling is an efficient post-processing-based calibration scheme and obtains well calibrated results. In this study, we leverage the concept of temperature scaling to build a sophisticated bin-wise scaling. Furthermore, we adopt augmentation of validation samples for elaborated scaling. The proposed methods consistently improve calibration performance with various datasets and deep convolutional neural network models.

📄 PDF Abstract BibTeX arXiv:1908.11528

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous Drivingimage-classificationImage ClassificationPrediction

Similar Papers 제목 키워드 기반

Quantile Adaptive Temperature Scaling for Confidence Calibration

2026-06-19 · Omprakash Chakraborty, Leo Fillioux, Ismail Ben Ayed, Jose Dolz arxiv

Deep neural networks often produce poorly calibrated confidence estimates, overstating their certainty even when predictions are incorrect. Temperature Scaling remains the most widely used posthoc calibration method due …

Beyond temperature scaling: Obtaining well-calibrated multiclass probabilities with Dirichlet calibration

2019-10-28 · Meelis Kull, Miquel Perello-Nieto, Markus Kängsepp, Telmo Silva Filho 외

Class probabilities predicted by most multiclass classifiers are uncalibrated, often tending towards over-confidence. With neural networks, calibration can be improved by temperature scaling, a method to learn a single c…

Binary Classification

Beyond temperature scaling: Obtaining well-calibrated multi-class probabilities with Dirichlet calibration

2019-12-01 · NeurIPS 2019 12 · Meelis Kull, Miquel Perello Nieto, Markus Kängsepp, Telmo Silva Filho 외

Class probabilities predicted by most multiclass classifiers are uncalibrated, often tending towards over-confidence. With neural networks, calibration can be improved by temperature scaling, a method to learn a single c…

Binary Classification

Does confidence calibration improve conformal prediction?

2024-02-06 · Huajun Xi, Jianguo Huang, Kangdao Liu, Lei Feng 외

Conformal prediction is an emerging technique for uncertainty quantification that constructs prediction sets guaranteed to contain the true label with a predefined probability. Previous works often employ temperature sca…

Conformal PredictionPredictionUncertainty Quantification

Sample-dependent Adaptive Temperature Scaling for Improved Calibration

2022-07-13 · Tom Joy, Francesco Pinto, Ser-Nam Lim, Philip H. S. Torr 외

It is now well known that neural networks can be wrong with high confidence in their predictions, leading to poor calibration. The most common post-hoc approach to compensate for this is to perform temperature scaling, w…

Out of Distribution (OOD) Detection