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.
Deep Probability Segmentation: Are segmentation models probability estimators? / Fassio, Simone; Monaco, Simone; Apiletti, Daniele. - (In corso di stampa). (Intervento presentato al convegno The 18th IEEE International Conference on Application of Information and Communication Technologies (AICT) tenutosi a Torino (ITA) nel 25-27 September 2024).
Deep Probability Segmentation: Are segmentation models probability estimators?
Simone Monaco;Daniele Apiletti
In corso di stampa
Abstract
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.File | Dimensione | Formato | |
---|---|---|---|
2409.12535v1.pdf
non disponibili
Tipologia:
2. Post-print / Author's Accepted Manuscript
Licenza:
Non Pubblico - Accesso privato/ristretto
Dimensione
261.1 kB
Formato
Adobe PDF
|
261.1 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/11583/2993010