Average Calibration Error: A Differentiable Loss for Improved Reliability in Image Segmentation
Deep neural networks for medical image segmentation often produce overconfident results misaligned with empirical observations. Such miscalibration, challenges their clinical translation. We propose to use marginal L1 average calibration error (mL1-ACE) as a novel auxiliary loss function to improve pixel-wise calibration without compromising segmentation quality. We show that this loss, despite using hard binning, is directly differentiable, bypassing the need for approximate but differentiable surrogate or soft binning approaches. Our work also introduces the concept of dataset reliability histograms which generalises standard reliability diagrams for refined visual assessment of calibration in semantic segmentation aggregated at the dataset level. Using mL1-ACE, we reduce average and maximum calibration error by 45% and 55% respectively, maintaining a Dice score of 87% on the BraTS 2021 dataset. We share our code here: https://github.com/cai4cai/ACE-DLIRIS
Code (1)
Tasks
Image SegmentationMedical Image SegmentationSegmentationSemantic SegmentationSimilar Papers 제목 키워드 기반
Revisiting Reweighted Risk for Calibration: AURC, Focal Loss, and Inverse Focal Loss
Several variants of reweighted risk functionals, such as focal losss, inverse focal loss, and the Area Under the Risk-Coverage Curve (AURC), have been proposed in the literature and claims have been made in relation to t…
Towards Unbiased Calibration using Meta-Regularization
Model miscalibration has been frequently identified in modern deep neural networks. Recent work aims to improve model calibration directly through a differentiable calibration proxy. However, the calibration produced is …
Meta-LearningRefine and Align: Confidence Calibration through Multi-Agent Interaction in VQA
In the context of Visual Question Answering (VQA) and Agentic AI, calibration refers to how closely an AI system's confidence in its answers reflects their actual correctness. This aspect becomes especially important whe…
Visual Question AnsweringExpert-Calibrated Learning for Online Optimization with Switching Costs
We study online convex optimization with switching costs, a practically important but also extremely challenging problem due to the lack of complete offline information. By tapping into the power of machine learning (ML)…
A Stitch in Time Saves Nine: A Train-Time Regularizing Loss for Improved Neural Network Calibration
Deep Neural Networks ( DNN s) are known to make overconfident mistakes, which makes their use problematic in safety-critical applications. State-of-the-art ( SOTA ) calibration techniques improve on the confidence of pre…
image-classificationImage ClassificationSemantic SegmentationVisual Question Answering