arXiv:2608. 10372v1 Announce Type: new Abstract: Post-hoc calibration aligns a classifier's predicted confidences with its empirical accuracy without retraining.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.
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.
The paper introduces SMART, a lightweight recalibration technique that adjusts logits based on the margin between the top two logits, called the logit gap. It uses a soft-binned Expected Calibration Error objective to balance bias and variance, enabling stable updates even with limited calibration data. Experiments across various datasets and architectures show SMART achieves state‑of‑the‑art calibration with fewer parameters than existing methods.
arXiv:2607. 07745v1 Announce Type: new Abstract: While accuracy, robustness, and calibration are all essential for reliable neural networks, they are often studied separately; developing models that satisfy all three simultaneously remains a central challenge.
Reliable confidence estimates are essential in semantic segmentation, especially in safety-critical settings where overconfident errors can mislead downstream decisions. Yet modern segmentation models often remain miscalibrated.
arXiv:2607. 01902v1 Announce Type: cross Abstract: Reliable confidence estimates are essential in semantic segmentation, especially in safety-critical settings where overconfident errors can mislead downstream decisions.
arXiv:2607. 23860v1 Announce Type: new Abstract: Deep ensembles provide the most reliable uncertainty estimates in deep learning, but their cost grows linearly with the number of members.