English
Related papers

Related papers: Confidence Calibration under Ambiguous Ground Trut…

200 papers

We introduce the notion of heterogeneous calibration that applies a post-hoc model-agnostic transformation to model outputs for improving AUC performance on binary classification tasks. We consider overconfident models, whose performance is…

Machine Learning · Statistics 2022-02-11 David Durfee , Aman Gupta , Kinjal Basu

While existing unsupervised domain adaptation (UDA) methods greatly enhance target domain performance in semantic segmentation, they often neglect network calibration quality, resulting in misalignment between prediction confidence and…

Computer Vision and Pattern Recognition · Computer Science 2026-02-25 Wangkai Li , Rui Sun , Zhaoyang Li , Yujia Chen , Tianzhu Zhang

The task of image segmentation is inherently noisy due to ambiguities regarding the exact location of boundaries between anatomical structures. We argue that this information can be extracted from the expert annotations at no extra cost,…

Computer Vision and Pattern Recognition · Computer Science 2021-04-14 Mobarakol Islam , Ben Glocker

Large Language Models (LLMs) show promise for automated grading, but their outputs can be unreliable. Rather than improving grading accuracy directly, we address a complementary problem: \textit{predicting when an LLM grader is likely to be…

Computation and Language · Computer Science 2026-04-01 Robinson Ferrer , Damla Turgut , Zhongzhou Chen , Shashank Sonkar

The Learning With Disagreements (LeWiDi) 2025 shared task aims to model annotator disagreement through soft label distribution prediction and perspectivist evaluation, which focuses on modeling individual annotators. We adapt DisCo…

Computation and Language · Computer Science 2025-10-07 Mandira Sawkar , Samay U. Shetty , Deepak Pandita , Tharindu Cyril Weerasooriya , Christopher M. Homan

Labeled datasets reflect the biases of their annotation pipelines, which sometimes introduce label bias: group-conditional label errors that cause systematic performance disparities across demographic subgroups. Label bias in image…

Computer Vision and Pattern Recognition · Computer Science 2026-05-11 Aditya Parikh , Stella Frank , Sneha Das , Aasa Feragen

State-of-the-art semi-supervised learning (SSL) approaches rely on highly confident predictions to serve as pseudo-labels that guide the training on unlabeled samples. An inherent drawback of this strategy stems from the quality of the…

Machine Learning · Computer Science 2024-03-26 Shambhavi Mishra , Balamurali Murugesan , Ismail Ben Ayed , Marco Pedersoli , Jose Dolz

Recently, learning with soft labels has been shown to achieve better performance than learning with hard labels in terms of model generalization, calibration, and robustness. However, collecting pointwise labeling confidence for all…

Machine Learning · Computer Science 2023-10-10 Wei Wang , Lei Feng , Yuchen Jiang , Gang Niu , Min-Ling Zhang , Masashi Sugiyama

Minimizing prediction uncertainty on unlabeled data is a key factor to achieve good performance in semi-supervised learning (SSL). The prediction uncertainty is typically expressed as the \emph{entropy} computed by the transformed…

Machine Learning · Computer Science 2021-12-16 Jing Li , Yuangang Pan , Ivor W. Tsang

Calibration is commonly evaluated by comparing model confidence with its empirical correctness, implicitly treating reliability as a function of the confidence score alone. However, this view can hide substantial structure: models may be…

Machine Learning · Computer Science 2026-05-14 Katarzyna Kobalczyk , Mihaela van der Schaar

Fully supervised object detection requires training images in which all instances are annotated. This is actually impractical due to the high labor and time costs and the unavoidable missing annotations. As a result, the incomplete…

Computer Vision and Pattern Recognition · Computer Science 2023-03-15 Haohan Wang , Liang Liu , Boshen Zhang , Jiangning Zhang , Wuhao Zhang , Zhenye Gan , Yabiao Wang , Chengjie Wang , Haoqian Wang

In supervised machine learning, models are typically trained using data with hard labels, i.e., definite assignments of class membership. This traditional approach, however, does not take the inherent uncertainty in these labels into…

Machine Learning · Computer Science 2024-09-25 Sjoerd de Vries , Dirk Thierens

Output uncertainty indicates whether the probabilistic properties reflect objective characteristics of the model output. Unlike most loss functions and metrics in machine learning, uncertainty pertains to individual samples, but validating…

Machine Learning · Computer Science 2024-12-23 Siyuan Zhang , Linbo Xie

Deep learning-based object detectors have achieved impressive performance in microscopy imaging, yet their confidence estimates often lack calibration, limiting their reliability for biomedical applications. In this work, we introduce a new…

Computer Vision and Pattern Recognition · Computer Science 2026-02-02 Francesco Campi , Lucrezia Tondo , Ekin Karabati , Johannes Betge , Marie Piraud

Automatic detection of speaker confidence is critical for adaptive computing but remains constrained by limited labelled data and the subjectivity of paralinguistic annotations. This paper proposes a semi-supervised hybrid framework that…

Sound · Computer Science 2026-05-13 Adam Wynn , Jingyun Wang

Neural networks for automated image segmentation are typically trained to achieve maximum accuracy, while less attention has been given to the calibration of their confidence scores. However, well-calibrated confidence scores provide…

Image and Video Processing · Electrical Eng. & Systems 2020-10-28 Axel-Jan Rousseau , Thijs Becker , Jeroen Bertels , Matthew B. Blaschko , Dirk Valkenborg

Large language models (LLMs) often make accurate next token predictions but their confidence in these predictions can be poorly calibrated: high-confidence predictions are frequently wrong, and low-confidence predictions may be correct.…

Machine Learning · Computer Science 2026-02-03 Nisarg Parikh , Ananya Sai , Pannaga Shivaswamy , Kunjal Panchal , Andrew Lan

A multiclass classifier is said to be top-label calibrated if the reported probability for the predicted class -- the top-label -- is calibrated, conditioned on the top-label. This conditioning on the top-label is absent in the closely…

Machine Learning · Computer Science 2022-09-07 Chirag Gupta , Aaditya Ramdas

While clustering is ubiquitously used across science and industry, uncertainty in cluster assignments is rarely quantified with rigorous guarantees. We propose a novel conformal inference framework for clustering that returns confidence…

Methodology · Statistics 2026-04-13 YoonHaeng Hur , Anirban Nath , Genevera Allen

Deep Neural Networks have significantly impacted many computer vision tasks. However, their effectiveness diminishes when test data distribution (target domain) deviates from the one of training data (source domain). In situations where…

Computer Vision and Pattern Recognition · Computer Science 2024-09-04 Andrea Maracani , Lorenzo Rosasco , Lorenzo Natale
‹ Prev 1 3 4 5 6 7 10 Next ›