paper-with-me

Papers

Kandinsky Conformal Prediction: Efficient Calibration of Image Segmentation Algorithms

2023-11-20 · CVPR 2024 1 · Joren Brunekreef, Eric Marcus, Ray Sheombarsing, Jan-Jakob Sonke, Jonas Teuwen

Image segmentation algorithms can be understood as a collection of pixel classifiers, for which the outcomes of nearby pixels are correlated. Classifier models can be calibrated using Inductive Conformal Prediction, but this requires holding back a sufficiently large calibration dataset for computing the distribution of non-conformity scores of the model's predictions. If one only requires only marginal calibration on the image level, this calibration set consists of all individual pixels in the images available for calibration. However, if the goal is to attain proper calibration for each individual pixel classifier, the calibration set consists of individual images. In a scenario where data are scarce (such as the medical domain), it may not always be possible to set aside sufficiently many images for this pixel-level calibration. The method we propose, dubbed `Kandinsky calibration'', makes use of the spatial structure present in the distribution of natural images to simultaneously calibrate the classifiers of `similar'' pixels. This can be seen as an intermediate approach between marginal (imagewise) and conditional (pixelwise) calibration, where non-conformity scores are aggregated over similar image regions, thereby making more efficient use of the images available for calibration. We run experiments on segmentation algorithms trained and calibrated on subsets of the public MS-COCO and Medical Decathlon datasets, demonstrating that Kandinsky calibration method can significantly improve the coverage. When compared to both pixelwise and imagewise calibration on little data, the Kandinsky method achieves much lower coverage errors, indicating the data efficiency of the Kandinsky calibration.

📄 PDF Abstract BibTeX arXiv:2311.11837

Code (1)

NKI-AI/kandinsky-calibration 공식 구현 pytorch

Tasks

Conformal PredictionImage SegmentationPredictionSemantic Segmentation

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Kandinsky Conformal Prediction: Beyond Class- and Covariate-Conditional Coverage

2025-02-24 · Konstantina Bairaktari, Jiayun Wu, Zhiwei Steven Wu

Conformal prediction is a powerful distribution-free framework for constructing prediction sets with coverage guarantees. Classical methods, such as split conformal prediction, provide marginal coverage, ensuring that th…

Conformal PredictionPrediction

Conformal Lesion Segmentation for 3D Medical Images

2025-10-19 · Binyu Tan, Zhiyuan Wang, Jinhao Duan, Kaidi Xu 외 arxiv

Medical image segmentation serves as a critical component of precision medicine, enabling accurate localization and delineation of pathological regions, such as lesions. However, existing models empirically apply fixed t…

Medical Image SegmentationLesion Segmentation

Controlling False Positives in Image Segmentation via Conformal Prediction

2025-11-19 · Luca Mossina, Corentin Friedrich arxiv

Reliable semantic segmentation is essential for clinical decision making, yet deep models rarely provide explicit statistical guarantees on their errors. We introduce a simple post-hoc framework that constructs confidenc…

Semantic SegmentationImage SegmentationDecision Making

Conditional Conformal Risk Adaptation

2025-04-10 · Rui Luo, Zhixin Zhou

Uncertainty quantification is becoming increasingly important in image segmentation, especially for high-stakes applications like medical imaging. While conformal risk control generalizes conformal prediction beyond stan…

Conformal PredictionImage SegmentationPersonalized SegmentationSegmentation+2

Robust Conformal Volume Estimation in 3D Medical Images

2024-07-29 · Benjamin Lambert, Florence Forbes, Senan Doyle, Michel Dojat

Volumetry is one of the principal downstream applications of 3D medical image segmentation, for example, to detect abnormal tissue growth or for surgery planning. Conformal Prediction is a promising framework for uncerta…

Conformal PredictionDensity Ratio EstimationImage SegmentationMedical Image Segmentation+2