Deep Probability Segmentation: Are segmentation models probability estimators?
Deep learning has revolutionized various fields by enabling highly accurate predictions and estimates. One important application is probabilistic prediction, where models estimate the probability of events rather than deterministic outcomes. This approach is particularly relevant and, therefore, still unexplored for segmentation tasks where each pixel in an image needs to be classified. Conventional models often overlook the probabilistic nature of labels, but accurate uncertainty estimation is crucial for improving the reliability and applicability of models. In this study, we applied Calibrated Probability Estimation (CaPE) to segmentation tasks to evaluate its impact on model calibration. Our results indicate that while CaPE improves calibration, its effect is less pronounced compared to classification tasks, suggesting that segmentation models can inherently provide better probability estimates. We also investigated the influence of dataset size and bin optimization on the effectiveness of calibration. Our results emphasize the expressive power of segmentation models as probability estimators and incorporate probabilistic reasoning, which is crucial for applications requiring precise uncertainty quantification.
Code (0)
등록된 구현이 없습니다.
Tasks
SegmentationUncertainty QuantificationSimilar Papers 제목 키워드 기반
Mask Propagation Network for Video Object Segmentation
In this work, we propose a mask propagation network to treat the video segmentation problem as a concept of the guided instance segmentation. Similar to most MaskTrack based video segmentation methods, our method takes t…
Instance SegmentationObjectOptical Flow EstimationSegmentation+4MFP: Making Full Use of Probability Maps for Interactive Image Segmentation
In recent interactive segmentation algorithms, previous probability maps are used as network input to help predictions in the current segmentation round. However, despite the utilization of previous masks, useful informa…
Image SegmentationInteractive SegmentationSegmentationSemantic SegmentationHypernet-Ensemble Learning of Segmentation Probability for Medical Image Segmentation with Ambiguous Labels
Despite the superior performance of Deep Learning (DL) on numerous segmentation tasks, the DL-based approaches are notoriously overconfident about their prediction with highly polarized label probability. This is often n…
Ensemble LearningImage SegmentationMedical Image SegmentationSegmentation+1H-EMD: A Hierarchical Earth Mover's Distance Method for Instance Segmentation
Deep learning (DL) based semantic segmentation methods have achieved excellent performance in biomedical image segmentation, producing high quality probability maps to allow extraction of rich instance information to fac…
Image SegmentationInstance SegmentationSegmentationSemantic SegmentationLocal Temperature Scaling for Probability Calibration
For semantic segmentation, label probabilities are often uncalibrated as they are typically only the by-product of a segmentation task. Intersection over Union (IoU) and Dice score are often used as criteria for segmenta…
Brain SegmentationSegmentationSemantic Segmentation