arXiv:2511. 22823v2 Announce Type: replace-cross Abstract: Weakly supervised learning has emerged as a practical alternative to fully supervised learning when complete and accurate labels are costly or infeasible to acquire.
arXiv:2512. 17788v2 Announce Type: replace Abstract: Multi-instance partial-label learning (MIPL) is a weakly supervised framework that extends the principles of multi-instance learning (MIL) and partial-label learning (PLL) to address the challenges of inexact supervision in both instance and label spaces.
arXiv:2609.26468v1 Announce Type: new Abstract: A key factor in deciding whether to trust an automatic prediction is its confidence score, which should be calibrated to match the actual probability o...
A key factor in deciding whether to trust an automatic prediction is its confidence score, which should be calibrated to match the actual probability of the prediction being correct. Most confidence c...
arXiv:2609.10333v1 Announce Type: new Abstract: Uncertainty estimation for medical vision--language models (VLMs) using conformal prediction has gained increasing attention due to its distribution-fr...
Uncertainty estimation for medical vision--language models (VLMs) using conformal prediction has gained increasing attention due to its distribution-free coverage guarantees. However, standard conform...
arXiv:2608. 03432v1 Announce Type: new Abstract: Refurbishment-based noisy-label learning mixes an observed label with a model-derived pseudo target, typically using one sample-wise cleanliness score to control both branches.
arXiv:2601. 11670v3 Announce Type: replace-cross Abstract: Pseudo-label selection in semi-supervised learning is commonly driven by maximum-confidence thresholds, yet confidence alone can be unreliable under model overconfidence and class imbalance.
arXiv:2607. 13423v1 Announce Type: new Abstract: Temperature scaling is the dominant post-hoc calibration method in modern deep learning.
arXiv:2610.19543v1 Announce Type: cross Abstract: In medical annotation and crowdsourcing, multiple annotators assign labels to each example, but these labels may be incorrect. Treating such noisy la...
The paper proposes a calibration-first framework that generates supervision scores without ground-truth labels or a shared annotation space. It aligns subset-specific scorers by mapping them onto a synthetic ordinal reference space built from ordered calibration features, enabling the fusion of otherwise incomparable outputs. Experiments on three benchmark datasets show that this method consistently outperforms uncalibrated averaging and matches or exceeds the best individual scorer, with significant improvements after Bonferroni correction.
arXiv:2605. 30188v2 Announce Type: replace-cross Abstract: Reliable probability estimates are critical in many machine learning applications, yet modern classifiers are often poorly calibrated.