Model Calibration in Dense Classification with Adaptive Label Perturbation

• URL: http://arxiv.org/abs/2307.13539v2
• Date: Thu, 3 Aug 2023 03:22:48 GMT
• Title: Model Calibration in Dense Classification with Adaptive Label Perturbation
• Authors: Jiawei Liu, Changkun Ye, Shan Wang, Ruikai Cui, Jing Zhang, Kaihao Zhang, Nick Barnes
• Abstract summary: Existing dense binary classification models are prone to being over-confident. We propose Adaptive Label Perturbation (ASLP) which learns a unique label perturbation level for each training image. ASLP can significantly improve calibration degrees of dense binary classification models on both in-distribution and out-of-distribution data.
• Score: 44.62722402349157
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: For safety-related applications, it is crucial to produce trustworthy deep neural networks whose prediction is associated with confidence that can represent the likelihood of correctness for subsequent decision-making. Existing dense binary classification models are prone to being over-confident. To improve model calibration, we propose Adaptive Stochastic Label Perturbation (ASLP) which learns a unique label perturbation level for each training image. ASLP employs our proposed Self-Calibrating Binary Cross Entropy (SC-BCE) loss, which unifies label perturbation processes including stochastic approaches (like DisturbLabel), and label smoothing, to correct calibration while maintaining classification rates. ASLP follows Maximum Entropy Inference of classic statistical mechanics to maximise prediction entropy with respect to missing information. It performs this while: (1) preserving classification accuracy on known data as a conservative solution, or (2) specifically improves model calibration degree by minimising the gap between the prediction accuracy and expected confidence of the target training label. Extensive results demonstrate that ASLP can significantly improve calibration degrees of dense binary classification models on both in-distribution and out-of-distribution data. The code is available on https://github.com/Carlisle-Liu/ASLP.

Related papers

• CALICO: Confident Active Learning with Integrated Calibration [11.978551396144532]
  We propose an AL framework that self-calibrates the confidence used for sample selection during the training process. We show improved classification performance compared to a softmax-based classifier with fewer labeled samples.
  arXiv  Detail & Related papers  (2024-07-02T15:05:19Z)
• Classifier Calibration with ROC-Regularized Isotonic Regression [0.0]
  We use isotonic regression to minimize the cross entropy on a calibration set via monotone transformations. IR acts as an adaptive binning procedure, which allows achieving a calibration error of zero, but leaves open the issue of the effect on performance. We show empirically that this general monotony criterion is effective in striking a balance between reducing cross entropy loss and avoiding overfitting of the calibration set.
  arXiv  Detail & Related papers  (2023-11-21T08:45:09Z)
• Generating Unbiased Pseudo-labels via a Theoretically Guaranteed Chebyshev Constraint to Unify Semi-supervised Classification and Regression [57.17120203327993]
  threshold-to-pseudo label process (T2L) in classification uses confidence to determine the quality of label. In nature, regression also requires unbiased methods to generate high-quality labels. We propose a theoretically guaranteed constraint for generating unbiased labels based on Chebyshev's inequality.
  arXiv  Detail & Related papers  (2023-11-03T08:39:35Z)
• Variational Classification [51.2541371924591]
  We derive a variational objective to train the model, analogous to the evidence lower bound (ELBO) used to train variational auto-encoders. Treating inputs to the softmax layer as samples of a latent variable, our abstracted perspective reveals a potential inconsistency. We induce a chosen latent distribution, instead of the implicit assumption found in a standard softmax layer.
  arXiv  Detail & Related papers  (2023-05-17T17:47:19Z)
• Adaptive Label Smoothing with Self-Knowledge in Natural Language Generation [16.878277421402945]
  We propose a regularization scheme that brings dynamic nature into the smoothing parameter. A model in training self-regulates the extent of smoothing on the fly during forward propagation.
  arXiv  Detail & Related papers  (2022-10-22T11:52:38Z)
• 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)
• Semi-supervised Contrastive Outlier removal for Pseudo Expectation Maximization (SCOPE) [2.33877878310217]
  We present a new approach to suppress confounding errors through a method we describe as Semi-supervised Contrastive Outlier removal for Pseudo Expectation Maximization (SCOPE) Our results show that SCOPE greatly improves semi-supervised classification accuracy over a baseline, and furthermore when combined with consistency regularization achieves the highest reported accuracy for the semi-supervised CIFAR-10 classification task using 250 and 4000 labeled samples.
  arXiv  Detail & Related papers  (2022-06-28T19:32:50Z)
• Confidence Calibration for Intent Detection via Hyperspherical Space and Rebalanced Accuracy-Uncertainty Loss [17.26964140836123]
  In some scenarios, users do not only care about the accuracy but also the confidence of model. We propose a model using the hyperspherical space and rebalanced accuracy-uncertainty loss. Our model outperforms the existing calibration methods and achieves a significant improvement on the calibration metric.
  arXiv  Detail & Related papers  (2022-03-17T12:01:33Z)
• Distribution-free uncertainty quantification for classification under label shift [105.27463615756733]
  We focus on uncertainty quantification (UQ) for classification problems via two avenues. We first argue that label shift hurts UQ, by showing degradation in coverage and calibration. We examine these techniques theoretically in a distribution-free framework and demonstrate their excellent practical performance.
  arXiv  Detail & Related papers  (2021-03-04T20:51:03Z)
• Calibration of Neural Networks using Splines [51.42640515410253]
  Measuring calibration error amounts to comparing two empirical distributions. We introduce a binning-free calibration measure inspired by the classical Kolmogorov-Smirnov (KS) statistical test. Our method consistently outperforms existing methods on KS error as well as other commonly used calibration measures.
  arXiv  Detail & Related papers  (2020-06-23T07:18:05Z)

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.