arXiv Machine Learning
Focal Calibration Loss: Controlling Posterior Distortion in Deep Neural Classifiers
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
Jun 18
Not Just How Much, But Where: Decomposing Epistemic Uncertainty into Per-Class Contributions
arXiv:2602. 21160v3 Announce Type: replace-cross Abstract: In safety-critical classification, the cost of failure is often asymmetric, yet Bayesian deep learning summarises epistemic uncertainty with a single scalar, mutual information (MI), that cannot distinguish whether a model's ignorance involves a benign or safety-critical class.
arXiv Machine Learning
Jul 7
Direct Bethe Free Energy Minimization for Bayesian Neural Networks
arXiv:2605. 08446v3 Announce Type: replace Abstract: Bayesian neural networks are typically trained against the evidence lower bound (ELBO), whose Jensen gap closes only when the variational posterior is exact.
arXiv Computer Vision
Sep 11
Confidence-Calibrating Regularization for Robust Brain MRI Segmentation Under Domain Shift
The paper introduces CalSAM, a lightweight adaptation framework that fine‑tunes only the mask decoder of the Segment Anything Model (SAM) while keeping its encoders frozen. CalSAM employs a Feature Fisher Information Penalty (FIP) to reduce encoder sensitivity to domain shift and a Confidence Misalignment Penalty (CMP) to curb overconfident voxel‑wise errors. Experiments on cross‑center, scanner‑shift, and motion‑corrupted brain MRI datasets show significant gains in Dice similarity coefficient, Hausdorff distance, and expected calibration error, with only a modest training‑time overhead.
arXiv Machine Learning
Sep 2
Let Confidence Change, Not the Prediction: Prediction-Preserving Repair for Post-hoc Calibration
arXiv:2609.01072v1 Announce Type: new Abstract: Post-hoc calibration corrects reported confidence, yet a multiclass calibrator can also change the associated top-1 prediction. Accuracy captures only...
arXiv Machine Learning
Jul 21
The Label Complexity of Class-Conditional Coverage under Distribution Shift
arXiv:2607. 18088v1 Announce Type: new Abstract: Standard evaluation of many recognition systems contains distribution shift by construction, since benchmarks place disjoint conditions in the training and test splits.
arXiv Machine Learning
Jul 21
The Calibration Channel Determines the Bayes-Error Proxy: An Exact Law for Temperature-Induced Distortion
arXiv:2607. 18162v1 Announce Type: new Abstract: The soft-label Bayes-error estimator beta(z) = E[min(z, 1-z)] of Ishida et al.