Torch-Uncertainty: A Deep Learning Framework for Uncertainty Quantification
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908650505764864 |
|---|---|
| author | Lafage, Adrien Laurent, Olivier Gabetni, Firas Franchi, Gianni |
| author_facet | Lafage, Adrien Laurent, Olivier Gabetni, Firas Franchi, Gianni |
| contents | Deep Neural Networks (DNNs) have demonstrated remarkable performance across various domains, including computer vision and natural language processing. However, they often struggle to accurately quantify the uncertainty of their predictions, limiting their broader adoption in critical real-world applications. Uncertainty Quantification (UQ) for Deep Learning seeks to address this challenge by providing methods to improve the reliability of uncertainty estimates. Although numerous techniques have been proposed, a unified tool offering a seamless workflow to evaluate and integrate these methods remains lacking. To bridge this gap, we introduce Torch-Uncertainty, a PyTorch and Lightning-based framework designed to streamline DNN training and evaluation with UQ techniques and metrics. In this paper, we outline the foundational principles of our library and present comprehensive experimental results that benchmark a diverse set of UQ methods across classification, segmentation, and regression tasks. Our library is available at https://github.com/ENSTA-U2IS-AI/Torch-Uncertainty |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_10282 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Torch-Uncertainty: A Deep Learning Framework for Uncertainty Quantification Lafage, Adrien Laurent, Olivier Gabetni, Firas Franchi, Gianni Machine Learning Artificial Intelligence Deep Neural Networks (DNNs) have demonstrated remarkable performance across various domains, including computer vision and natural language processing. However, they often struggle to accurately quantify the uncertainty of their predictions, limiting their broader adoption in critical real-world applications. Uncertainty Quantification (UQ) for Deep Learning seeks to address this challenge by providing methods to improve the reliability of uncertainty estimates. Although numerous techniques have been proposed, a unified tool offering a seamless workflow to evaluate and integrate these methods remains lacking. To bridge this gap, we introduce Torch-Uncertainty, a PyTorch and Lightning-based framework designed to streamline DNN training and evaluation with UQ techniques and metrics. In this paper, we outline the foundational principles of our library and present comprehensive experimental results that benchmark a diverse set of UQ methods across classification, segmentation, and regression tasks. Our library is available at https://github.com/ENSTA-U2IS-AI/Torch-Uncertainty |
| title | Torch-Uncertainty: A Deep Learning Framework for Uncertainty Quantification |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2511.10282 |