Where are we with calibration under dataset shift in image classification?

• URL: http://arxiv.org/abs/2507.07780v1
• Date: Thu, 10 Jul 2025 13:59:53 GMT
• Title: Where are we with calibration under dataset shift in image classification?
• Authors: Mélanie Roschewitz, Raghav Mehta, Fabio de Sousa Ribeiro, Ben Glocker,
• Abstract summary: We conduct a study on the state of calibration under real-world dataset shift for image classification.<n>We compare various post-hoc calibration methods, and their interactions with common in-training calibration strategies.<n>We find that: (i) applying calibration prior to ensembling is more effective for calibration under shifts.
• Score: 16.571507609650073
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We conduct an extensive study on the state of calibration under real-world dataset shift for image classification. Our work provides important insights on the choice of post-hoc and in-training calibration techniques, and yields practical guidelines for all practitioners interested in robust calibration under shift. We compare various post-hoc calibration methods, and their interactions with common in-training calibration strategies (e.g., label smoothing), across a wide range of natural shifts, on eight different classification tasks across several imaging domains. We find that: (i) simultaneously applying entropy regularisation and label smoothing yield the best calibrated raw probabilities under dataset shift, (ii) post-hoc calibrators exposed to a small amount of semantic out-of-distribution data (unrelated to the task) are most robust under shift, (iii) recent calibration methods specifically aimed at increasing calibration under shifts do not necessarily offer significant improvements over simpler post-hoc calibration methods, (iv) improving calibration under shifts often comes at the cost of worsening in-distribution calibration. Importantly, these findings hold for randomly initialised classifiers, as well as for those finetuned from foundation models, the latter being consistently better calibrated compared to models trained from scratch. Finally, we conduct an in-depth analysis of ensembling effects, finding that (i) applying calibration prior to ensembling (instead of after) is more effective for calibration under shifts, (ii) for ensembles, OOD exposure deteriorates the ID-shifted calibration trade-off, (iii) ensembling remains one of the most effective methods to improve calibration robustness and, combined with finetuning from foundation models, yields best calibration results overall.

Related papers

• Calibration by Distribution Matching: Trainable Kernel Calibration Metrics [56.629245030893685]
  We introduce kernel-based calibration metrics that unify and generalize popular forms of calibration for both classification and regression. These metrics admit differentiable sample estimates, making it easy to incorporate a calibration objective into empirical risk minimization. We provide intuitive mechanisms to tailor calibration metrics to a decision task, and enforce accurate loss estimation and no regret decisions.
  arXiv  Detail & Related papers  (2023-10-31T06:19:40Z)
• Adaptive Calibrator Ensemble for Model Calibration under Distribution Shift [23.794897699193875]
  adaptive calibrator ensemble (ACE) calibrates OOD datasets whose difficulty is usually higher than the calibration set. ACE generally improves the performance of a few state-of-the-art calibration schemes on a series of OOD benchmarks.
  arXiv  Detail & Related papers  (2023-03-09T15:22:02Z)
• Bag of Tricks for In-Distribution Calibration of Pretrained Transformers [8.876196316390493]
  We present an empirical study on confidence calibration for pre-trained language models (PLMs) We find that the ensemble model overfitted to the training set shows sub-par calibration performance. We propose the Calibrated PLM (CALL), a combination of calibration techniques.
  arXiv  Detail & Related papers  (2023-02-13T21:11:52Z)
• On Calibrating Semantic Segmentation Models: Analyses and An Algorithm [51.85289816613351]
  We study the problem of semantic segmentation calibration. Model capacity, crop size, multi-scale testing, and prediction correctness have impact on calibration. We propose a simple, unifying, and effective approach, namely selective scaling.
  arXiv  Detail & Related papers  (2022-12-22T22:05:16Z)
• Localized Calibration: Metrics and Recalibration [133.07044916594361]
  We propose a fine-grained calibration metric that spans the gap between fully global and fully individualized calibration. We then introduce a localized recalibration method, LoRe, that improves the LCE better than existing recalibration methods.
  arXiv  Detail & Related papers  (2021-02-22T07:22:12Z)
• Post-hoc Uncertainty Calibration for Domain Drift Scenarios [46.88826364244423]
  We show that existing post-hoc calibration methods yield highly over-confident predictions under domain shift. We introduce a simple strategy where perturbations are applied to samples in the validation set before performing the post-hoc calibration step.
  arXiv  Detail & Related papers  (2020-12-20T18:21:13Z)
• Uncertainty Quantification and Deep Ensembles [79.4957965474334]
  We show that deep-ensembles do not necessarily lead to improved calibration properties. We show that standard ensembling methods, when used in conjunction with modern techniques such as mixup regularization, can lead to less calibrated models. This text examines the interplay between three of the most simple and commonly used approaches to leverage deep learning when data is scarce.
  arXiv  Detail & Related papers  (2020-07-17T07:32:24Z)
• Unsupervised Calibration under Covariate Shift [92.02278658443166]
  We introduce the problem of calibration under domain shift and propose an importance sampling based approach to address it. We evaluate and discuss the efficacy of our method on both real-world datasets and synthetic datasets.
  arXiv  Detail & Related papers  (2020-06-29T21:50:07Z)
• 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.