Invertible Logits Transformation for Accuracy-Preserving Post-Hoc Uncertainty Calibration

arXiv:2608.10372v1 Announce Type: new Abstract: Post-hoc calibration aligns a classifier's predicted confidences with its empirical accuracy without retraining. An ideal calibrator should correct nonlinear miscalibration, scale gracefully to large label spaces, and preserve the original predictions; existing methods typically violate at least one of these properties---temperature scaling lacks expressivity, more flexible parametric alternatives introduce parameters that grow with the number of classes C, and other expressive methods do not preserve the rank ordering of class scores and may alter the predicted class. We propose extbf{Invertible Logits Transformation (InvLT)}, which applies a learned scalar MLP f:RoR element-wise to the pre-softmax logits. Sharing f across all logit dimensions makes the parameter count independent of C. Monotonicity of f---and hence preservation of the argmax prediction---is softly encouraged via a paired inverse network rather than enforced through the numerical integration required by prior monotone calibrators; this avoids their computational overhead while empirically preserving the original classification accuracy in every setting we evaluate. Across standard image classification benchmarks and a range of architectures, InvLT consistently outperforms a broad set of post-hoc baselines on standard calibration metrics.

Related

• Evaluating the Quality of the Quantified Uncertainty for (Re)Calibration of Data-Driven Regression Models
• TwinTrack: Post-hoc Multi-Rater Calibration for Medical Image Segmentation
• Conformal Bayes under Label Shift: Post-Hoc Calibration vs. In-Training Adaptation

Source: arXiv cs.LG | 2026-08-12