Skip to main navigation Skip to search Skip to main content

Uncertainty Weighted Gradients for Model Calibration

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

Abstract

Model calibration is essential for ensuring that the predictions of deep neural networks accurately reflect true probabilities in real-world classification tasks. However, deep networks often produce over-confident or under-confident predictions, leading to miscalibration. Various methods have been proposed to address this issue by designing effective loss functions for calibration, such as focal loss. In this paper, we analyze its effectiveness and provide a unified loss framework of focal loss and its variants, where we mainly attribute their superiority in model calibration to the loss weighting factor that estimates sample-wise uncertainty. Based on our analysis, existing loss functions fail to achieve optimal calibration performance due to two main issues: including misalignment during optimization and insufficient precision in uncertainty estimation. Specifically, focal loss cannot align sample uncertainty with gradient scaling and the single logit cannot indicate the uncertainty. To address these issues, we reformulate the optimization from the perspective of gradients, which focuses on uncertain samples. Meanwhile, we propose using the Brier Score as the loss weight factor, which provides a more accurate uncertainty estimation via all the logits. Extensive experiments on various models and datasets demonstrate that our method achieves state-of-the-art (SOTA) performance. ©2025 IEEE
Original languageEnglish
Title of host publication2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
PublisherIEEE
Pages15497-15507
Number of pages11
ISBN (Electronic)979-8-3315-4364-8
DOIs
Publication statusPublished - 13 Aug 2025
Event2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2025) - Music City Center, Nashville, United States
Duration: 11 Jun 2025 → 15 Jun 2025
https://cvpr.thecvf.com/Conferences/2025
https://cvpr.thecvf.com/

Publication series

NameProceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online)
ISSN (Electronic)2575-7075

Conference

Conference2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2025)
Abbreviated titleCVPR2025
PlaceUnited States
CityNashville
Period11/06/25 → 15/06/25
Internet address

Bibliographical note

Full text of this publication does not contain sufficient affiliation information. With consent from the author(s) concerned, the Research Unit(s) information for this record is based on the existing academic department affiliation of the author(s)

Funding

This work was supported in part by the Start-up Grant (No. 9610680) of the City University of Hong Kong, Young Scientist Fund (No. 62406265) of NSFC, and the Australian Research Council under Projects DP240101848 and FT230100549.

Fingerprint

Dive into the research topics of 'Uncertainty Weighted Gradients for Model Calibration'. Together they form a unique fingerprint.

Cite this