Confidence Calibration with Bounded Error Using Transformations

• URL: http://arxiv.org/abs/2102.12680v1
• Date: Thu, 25 Feb 2021 04:40:27 GMT
• Title: Confidence Calibration with Bounded Error Using Transformations
• Authors: Sooyong Jang, Radoslav Ivanov, Insup lee, and James Weimer
• Abstract summary: We introduce Hoki, a novel calibration algorithm with a theoretical bound on the calibration error (CE) We show that Hoki generally outperforms state-of-the-art calibration algorithms across multiple datasets and models. In addition, Hoki is fast algorithm which is comparable to temperature scaling in terms of learning time.
• Score: 4.278591555984394
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As machine learning techniques become widely adopted in new domains, especially in safety-critical systems such as autonomous vehicles, it is crucial to provide accurate output uncertainty estimation. As a result, many approaches have been proposed to calibrate neural networks to accurately estimate the likelihood of misclassification. However, while these methods achieve low expected calibration error (ECE), few techniques provide theoretical performance guarantees on the calibration error (CE). In this paper, we introduce Hoki, a novel calibration algorithm with a theoretical bound on the CE. Hoki works by transforming the neural network logits and/or inputs and recursively performing calibration leveraging the information from the corresponding change in the output. We provide a PAC-like bounds on CE that is shown to decrease with the number of samples used for calibration, and increase proportionally with ECE and the number of discrete bins used to calculate ECE. We perform experiments on multiple datasets, including ImageNet, and show that the proposed approach generally outperforms state-of-the-art calibration algorithms across multiple datasets and models - providing nearly an order or magnitude improvement in ECE on ImageNet. In addition, Hoki is fast algorithm which is comparable to temperature scaling in terms of learning time.

Related papers

• Classifier Ensemble for Efficient Uncertainty Calibration of Deep Neural Networks for Image Classification [1.0649605625763086]
  We evaluate both accuracy and calibration metrics, focusing on Expected Error (ECE) and Maximum Error (MCE) Our work compares different methods for building simple yet efficient classifier ensembles, including majority voting and several metamodel-based approaches.
  arXiv  Detail & Related papers  (2025-01-17T10:16:18Z)
• Consistency Calibration: Improving Uncertainty Calibration via Consistency among Perturbed Neighbors [22.39558434131574]
  We introduce the concept of consistency as an alternative perspective on model calibration. We propose a post-hoc calibration method called Consistency (CC) which adjusts confidence based on the model's consistency across inputs. We show that performing perturbations at the logit level significantly improves computational efficiency.
  arXiv  Detail & Related papers  (2024-10-16T06:55:02Z)
• Accelerating Error Correction Code Transformers [56.75773430667148]
  We introduce a novel acceleration method for transformer-based decoders. We achieve a 90% compression ratio and reduce arithmetic operation energy consumption by at least 224 times on modern hardware.
  arXiv  Detail & Related papers  (2024-10-08T11:07:55Z)
• ForeCal: Random Forest-based Calibration for DNNs [0.0]
  We propose ForeCal, a novel post-hoc calibration algorithm based on Random forests. ForeCal exploits two unique properties of Random forests: the ability to enforce weak monotonicity and range-preservation. We show that ForeCal outperforms existing methods in terms of Expected Error(ECE) with minimal impact on the discriminative power of the base as measured by AUC.
  arXiv  Detail & Related papers  (2024-09-04T04:56:41Z)
• Cal-DETR: Calibrated Detection Transformer [67.75361289429013]
  We propose a mechanism for calibrated detection transformers (Cal-DETR), particularly for Deformable-DETR, UP-DETR and DINO. We develop an uncertainty-guided logit modulation mechanism that leverages the uncertainty to modulate the class logits. Results corroborate the effectiveness of Cal-DETR against the competing train-time methods in calibrating both in-domain and out-domain detections.
  arXiv  Detail & Related papers  (2023-11-06T22:13:10Z)
• Calibration of Neural Networks [77.34726150561087]
  This paper presents a survey of confidence calibration problems in the context of neural networks. We analyze problem statement, calibration definitions, and different approaches to evaluation. Empirical experiments cover various datasets and models, comparing calibration methods according to different criteria.
  arXiv  Detail & Related papers  (2023-03-19T20:27:51Z)
• Sharp Calibrated Gaussian Processes [58.94710279601622]
  State-of-the-art approaches for designing calibrated models rely on inflating the Gaussian process posterior variance. We present a calibration approach that generates predictive quantiles using a computation inspired by the vanilla Gaussian process posterior variance. Our approach is shown to yield a calibrated model under reasonable assumptions.
  arXiv  Detail & Related papers  (2023-02-23T12:17:36Z)
• Sample-dependent Adaptive Temperature Scaling for Improved Calibration [95.7477042886242]
  Post-hoc approach to compensate for neural networks being wrong is to perform temperature scaling. We propose to predict a different temperature value for each input, allowing us to adjust the mismatch between confidence and accuracy. We test our method on the ResNet50 and WideResNet28-10 architectures using the CIFAR10/100 and Tiny-ImageNet datasets.
  arXiv  Detail & Related papers  (2022-07-13T14:13:49Z)
• Soft Calibration Objectives for Neural Networks [40.03050811956859]
  We propose differentiable losses to improve calibration based on a soft (continuous) version of the binning operation underlying popular calibration-error estimators. When incorporated into training, these soft calibration losses achieve state-of-the-art single-model ECE across multiple datasets with less than 1% decrease in accuracy.
  arXiv  Detail & Related papers  (2021-07-30T23:30:20Z)
• Parameterized Temperature Scaling for Boosting the Expressive Power in Post-Hoc Uncertainty Calibration [57.568461777747515]
  We introduce a novel calibration method, Parametrized Temperature Scaling (PTS) We demonstrate that the performance of accuracy-preserving state-of-the-art post-hoc calibrators is limited by their intrinsic expressive power. We show with extensive experiments that our novel accuracy-preserving approach consistently outperforms existing algorithms across a large number of model architectures, datasets and metrics.
  arXiv  Detail & Related papers  (2021-02-24T10:18:30Z)
• Multi-Class Uncertainty Calibration via Mutual Information Maximization-based Binning [8.780958735684958]
  Post-hoc multi-class calibration is a common approach for providing confidence estimates of deep neural network predictions. Recent work has shown that widely used scaling methods underestimate their calibration error. We propose a shared class-wise (sCW) calibration strategy, sharing one calibrator among similar classes.
  arXiv  Detail & Related papers  (2020-06-23T15:31:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.