Cover Image

Improving Calibration by Relating Focal Loss, Temperature Scaling, and Properness

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Komisarenko, Viacheslav, Kull, Meelis
Format:	Preprint
Published:	2024
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Aligning the Evaluation of Probabilistic Predictions with Downstream Value
by: Shahroudi, Novin, et al.
Published: (2025)

On the Usefulness of the Fit-on-the-Test View on Evaluating Calibration of Classifiers
by: Kängsepp, Markus, et al.
Published: (2022)

Cautious Calibration in Binary Classification
by: Allikivi, Mari-Liis, et al.
Published: (2024)

Probability Density from Latent Diffusion Models for Out-of-Distribution Detection
by: Järve, Joonas, et al.
Published: (2025)

Cross-model Fairness: Empirical Study of Fairness and Ethics Under Model Multiplicity
by: Sokol, Kacper, et al.
Published: (2022)

How Uncertainty Estimation Scales with Sampling in Reasoning Models
by: Del, Maksym, et al.
Published: (2026)

Geometric Insights into Focal Loss: Reducing Curvature for Enhanced Model Calibration
by: Kimura, Masanari, et al.
Published: (2024)

Enhancing web traffic attacks identification through ensemble methods and feature selection
by: Urda, Daniel, et al.
Published: (2024)

Leveraging Geometric Insights in Hyperbolic Triplet Loss for Improved Recommendations
by: Yusupov, Viacheslav, et al.
Published: (2025)

Improving Performance in Classification Tasks with LCEN and the Weighted Focal Differentiable MCC Loss
by: Seber, Pedro, et al.
Published: (2026)

Sample-Efficient Omniprediction for Proper Losses
by: Gibbs, Isaac, et al.
Published: (2025)

Better Uncertainty Calibration via Proper Scores for Classification and Beyond
by: Gruber, Sebastian G., et al.
Published: (2022)

Evaluating Posterior Probabilities: Decision Theory, Proper Scoring Rules, and Calibration
by: Ferrer, Luciana, et al.
Published: (2024)

GETS: Ensemble Temperature Scaling for Calibration in Graph Neural Networks
by: Zhuang, Dingyi, et al.
Published: (2024)

Generative Cross-Entropy: A Strictly Proper Loss for Data-Efficient Classification
by: Zhan, Qipeng, et al.
Published: (2026)

DATS: Distance-Aware Temperature Scaling for Calibrated Class-Incremental Learning
by: Serra, Giuseppe, et al.
Published: (2025)

Calibrating Language Models with Adaptive Temperature Scaling
by: Xie, Johnathan, et al.
Published: (2024)

Calibrating Where It Matters: Constrained Temperature Scaling
by: McKenna, Stephen, et al.
Published: (2024)

T-CIL: Temperature Scaling using Adversarial Perturbation for Calibration in Class-Incremental Learning
by: Hwang, Seong-Hyeon, et al.
Published: (2025)

Neural Clamping: Joint Input Perturbation and Temperature Scaling for Neural Network Calibration
by: Tang, Yung-Chen, et al.
Published: (2022)

Loss-Controlling Calibration for Predictive Models
by: Wang, Di, et al.
Published: (2023)

WATS: Calibrating Graph Neural Networks with Wavelet-Aware Temperature Scaling
by: Li, Xiaoyang, et al.
Published: (2025)

Focal-SAM: Focal Sharpness-Aware Minimization for Long-Tailed Classification
by: Li, Sicong, et al.
Published: (2025)

Robust Layerwise Scaling Rules by Proper Weight Decay Tuning
by: Fan, Zhiyuan, et al.
Published: (2025)

EnsLoss: Stochastic Calibrated Loss Ensembles for Preventing Overfitting in Classification
by: Dai, Ben
Published: (2024)

Improving Diversity in Language Models: When Temperature Fails, Change the Loss
by: Verine, Alexandre, et al.
Published: (2025)

On the Calibration of Epistemic Uncertainty: Principles, Paradoxes and Conflictual Loss
by: Fellaji, Mohammed, et al.
Published: (2024)

Dimension-Free Decision Calibration for Nonlinear Loss Functions
by: Tang, Jingwu, et al.
Published: (2025)

Average Calibration Error: A Differentiable Loss for Improved Reliability in Image Segmentation
by: Barfoot, Theodore, et al.
Published: (2024)

Flexible Distribution Alignment: Towards Long-tailed Semi-supervised Learning with Proper Calibration
by: Aimar, Emanuel Sanchez, et al.
Published: (2023)

Modern Neural Networks for Small Tabular Datasets: The New Default for Field-Scale Digital Soil Mapping?
by: Barkov, Viacheslav, et al.
Published: (2025)

Consistency-Guided Temperature Scaling Using Style and Content Information for Out-of-Domain Calibration
by: Choi, Wonjeong, et al.
Published: (2024)

Towards Calibrated Losses for Adversarial Robust Reject Option Classification
by: Shah, Vrund, et al.
Published: (2024)

Machine Learning (ML) library in Linux kernel
by: Dubeyko, Viacheslav
Published: (2026)

Proper Learnability and the Role of Unlabeled Data
by: Asilis, Julian, et al.
Published: (2025)

Proper Latent Decomposition
by: Kelshaw, Daniel, et al.
Published: (2024)

OrthoGrad Improves Neural Calibration
by: Hedges, C. Evans
Published: (2025)

Expectation Consistency Loss: Rethink Confidence Calibration under Covariate Shift
by: Dong, Jinzong, et al.
Published: (2026)

Focal Loss based Residual Convolutional Neural Network for Speech Emotion Recognition
by: Tripathi, Suraj, et al.
Published: (2019)

Temperature-Free Loss Function for Contrastive Learning
by: Kim, Bum Jun, et al.
Published: (2025)