中文
相关论文

相关论文: On the Calibration of Uncertainty Estimation in Li…

200 篇论文

Deep metric learning has gained promising improvement in recent years following the success of deep learning. It has been successfully applied to problems in few-shot learning, image retrieval, and open-set classifications. However,…

机器学习 · 计算机科学 2020-06-11 Maryna Karpusha , Sunghee Yun , Istvan Fehervari

The use of deep learning for medical imaging has seen tremendous growth in the research community. One reason for the slow uptake of these systems in the clinical setting is that they are complex, opaque and tend to fail silently. Outside…

计算机视觉与模式识别 · 计算机科学 2018-07-03 Terrance DeVries , Graham W. Taylor

Unbiased confidence estimates of neural networks are crucial especially for safety-critical applications. Many methods have been developed to calibrate biased confidence estimates. Though there is a variety of methods for classification,…

计算机视觉与模式识别 · 计算机科学 2020-12-15 Fabian Küppers , Jan Kronenberger , Amirhossein Shantia , Anselm Haselhoff

Data-driven methods have achieved notable performance on intent detection, which is a task to comprehend user queries. Nonetheless, they are controversial for over-confident predictions. In some scenarios, users do not only care about the…

计算与语言 · 计算机科学 2022-03-18 Yantao Gong , Cao Liu , Fan Yang , Xunliang Cai , Guanglu Wan , Jiansong Chen , Weipeng Zhang , Houfeng Wang

In the domain of computer vision, semantic segmentation emerges as a fundamental application within machine learning, wherein individual pixels of an image are classified into distinct semantic categories. This task transcends traditional…

人工智能 · 计算机科学 2024-04-09 Qitian Ma , Shyam Nanda Rai , Carlo Masone , Tatiana Tommasi

Deep learning (DL) has recently attracted increasing interest to improve object type classification for automotive radar.In addition to high accuracy, it is crucial for decision making in autonomous vehicles to evaluate the reliability of…

机器学习 · 计算机科学 2021-06-11 Kanil Patel , William Beluch , Kilian Rambach , Adriana-Eliza Cozma , Michael Pfeiffer , Bin Yang

Sequence generation models are increasingly being used to translate natural language into programs, i.e. to perform executable semantic parsing. The fact that semantic parsing aims to predict programs that can lead to executed actions in…

计算与语言 · 计算机科学 2023-07-10 Elias Stengel-Eskin , Benjamin Van Durme

Calibration is central to reliable semantic uncertainty quantification, yet prior work has largely focused on discrimination, neglecting calibration. As calibration and discrimination capture distinct aspects of uncertainty, focusing on…

机器学习 · 计算机科学 2026-04-09 Tom A. Lamb , Desi R. Ivanova , Philip H. S. Torr , Tim G. J. Rudner

Despite the great success of state-of-the-art deep neural networks, several studies have reported models to be over-confident in predictions, indicating miscalibration. Label Smoothing has been proposed as a solution to the over-confidence…

计算机视觉与模式识别 · 计算机科学 2023-01-31 Shuang Ao , Stefan Rueger , Advaith Siddharthan

Semi-supervised segmentation tackles the scarcity of annotations by leveraging unlabeled data with a small amount of labeled data. A prominent way to utilize the unlabeled data is by consistency training which commonly uses a…

计算机视觉与模式识别 · 计算机科学 2022-03-14 Sukesh Adiga , Jose Dolz , Herve Lombaert

While the accuracy of modern deep learning models has significantly improved in recent years, the ability of these models to generate uncertainty estimates has not progressed to the same degree. Uncertainty methods are designed to provide…

机器学习 · 统计学 2020-06-17 Adam M. Oberman , Chris Finlay , Alexander Iannantuono , Tiago Salvador

The proliferation of Deep Neural Networks has resulted in machine learning systems becoming increasingly more present in various real-world applications. Consequently, there is a growing demand for highly reliable models in many domains,…

计算机视觉与模式识别 · 计算机科学 2024-03-19 Pedro Conde , Rui L. Lopes , Cristiano Premebida

In this work, we for the first time present a method for detecting label errors in image datasets with semantic segmentation, i.e., pixel-wise class labels. Annotation acquisition for semantic segmentation datasets is time-consuming and…

计算机视觉与模式识别 · 计算机科学 2024-08-27 Matthias Rottmann , Marco Reese

Proper confidence calibration of deep neural networks is essential for reliable predictions in safety-critical tasks. Miscalibration can lead to model over-confidence and/or under-confidence; i.e., the model's confidence in its prediction…

机器学习 · 计算机科学 2023-08-08 Shuang Ao , Stefan Rueger , Advaith Siddharthan

For classification models based on neural networks, the maximum predicted class probability is often used as a confidence score. This score rarely predicts well the probability of making a correct prediction and requires a post-processing…

机器学习 · 计算机科学 2024-11-07 Adrien LeCoz , Stéphane Herbin , Faouzi Adjed

3D semantic segmentation (3DSS) is an essential process in the creation of a safe autonomous driving system. However, deep learning models for 3D semantic segmentation often suffer from the class imbalance problem and out-of-distribution…

计算机视觉与模式识别 · 计算机科学 2022-03-02 Yancheng Pan , Fan Xie , Huijing Zhao

Accurate probabilistic predictions can be characterized by two properties -- calibration and sharpness. However, standard maximum likelihood training yields models that are poorly calibrated and thus inaccurate -- a 90% confidence interval…

机器学习 · 计算机科学 2025-05-14 Volodymyr Kuleshov , Shachi Deshpande

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…

计算机视觉与模式识别 · 计算机科学 2024-09-20 Simone Fassio , Simone Monaco , Daniele Apiletti

With rapid adoption of deep learning in critical applications, the question of when and how much to trust these models often arises, which drives the need to quantify the inherent uncertainties. While identifying all sources that account…

Safety-critical applications such as autonomous driving require robust 3D environment perception algorithms capable of handling diverse and ambiguous surroundings. The predictive performance of classification models is heavily influenced by…

计算机视觉与模式识别 · 计算机科学 2024-08-02 Mariella Dreissig , Simon Ruehle , Florian Piewak , Joschka Boedecker