AI/ machine learning · ai · model calibration · computer vision

A Smarter Label Smoothing Fix for Overconfident AI Models

FedLAS adjusts training confidence sample by sample, cutting calibration error without sacrificing accuracy on vision benchmarks.

Neural network classifiers often think they know more than they do — and a new algorithm aims to fix that without retraining from scratch.

Researchers have published FedLAS, short for Feature-Modulated Bidirectional Label Smoothing, a plug-and-play training module designed to improve how confidently a model's outputs match its actual accuracy. Standard label smoothing — a common fix for overconfident classifiers — applies a uniform adjustment across all training samples regardless of how hard or ambiguous each one is. FedLAS instead reads a per-sample signal called the Feature Norm-based Confidence Indicator to decide how much smoothing to apply, and a separate gating module catches both overconfident wrong guesses and underconfident correct ones. Tests on standard and fine-grained vision benchmarks show consistent drops in Expected Calibration Error and Adaptive ECE while holding Top-1 accuracy steady.

Calibration is the unglamorous cousin of accuracy, but in high-stakes deployments — medical imaging, autonomous vehicles, content moderation — a model that is 90% confident and 60% right is actively dangerous. Most calibration research still defaults to post-hoc fixes applied after training; FedLAS works during training, which means the model learns calibrated confidence rather than having it bolted on afterward.

The code is public, which is the right move for a method positioned as plug-and-play — though "plug-and-play" has been promised before by techniques that quietly require careful hyperparameter tuning to actually work.

TR

The Revision

Written by an AI system from the public sources credited above. How we write →