# Beyond One-Hot Labels: Semantic Mixing for Model Calibration

arXiv: https://arxiv.org/abs/2504.13548 · HTML: https://mlsanity.com/paper/2504.13548/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 51 of its 65 references that are in the map.
- First posted on arXiv 18 Apr 2025.

## Builds on (most cited first, 30 of 51)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations](https://mlsanity.com/paper/2108.01073/) (2021)
- [Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift](https://mlsanity.com/paper/1906.02530/) (2019)
- [When Does Label Smoothing Help?](https://mlsanity.com/paper/1906.02629/) (2019)
- [AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty](https://mlsanity.com/paper/1912.02781/) (2019)
- [Regularizing Neural Networks by Penalizing Confident Output Distributions](https://mlsanity.com/paper/1701.06548/) (2017)
- [Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness](https://mlsanity.com/paper/2006.10108/) (2020)
- [Beyond temperature scaling: Obtaining well-calibrated multiclass probabilities with Dirichlet calibration](https://mlsanity.com/paper/1910.12656/) (2019)
- [Calibrating Deep Neural Networks using Focal Loss](https://mlsanity.com/paper/2002.09437/) (2020)
- [Is synthetic data from generative models ready for image recognition?](https://mlsanity.com/paper/2210.07574/) (2022)
- [Your Diffusion Model is Secretly a Zero-Shot Classifier](https://mlsanity.com/paper/2303.16203/) (2023)
- [On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networks](https://mlsanity.com/paper/1905.11001/) (2019)
- [Effective Data Augmentation With Diffusion Models](https://mlsanity.com/paper/2302.07944/) (2023)
- [Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup](https://mlsanity.com/paper/2009.06962/) (2020)
- [Mitigating Neural Network Overconfidence with Logit Normalization](https://mlsanity.com/paper/2205.09310/) (2022)
- [Improving Calibration for Long-Tailed Recognition](https://mlsanity.com/paper/2104.00466/) (2021)
- [Better Diffusion Models Further Improve Adversarial Training](https://mlsanity.com/paper/2302.04638/) (2023)
- [Evaluating model calibration in classification](https://mlsanity.com/paper/1902.06977/) (2019)
- [SaliencyMix: A Saliency Guided Data Augmentation Strategy for Better Regularization](https://mlsanity.com/paper/2006.01791/) (2020)
- [Deep Image Retrieval: Learning global representations for image search](https://mlsanity.com/paper/1604.01325/) (2016)
- [Remix: Rebalanced Mixup](https://mlsanity.com/paper/2007.03943/) (2020)

## Built on by (most cited first, 2 of 2)

- [Sample Margin-Aware Recalibration of Temperature Scaling](https://mlsanity.com/paper/2506.23492/) (2025)
- [Calibration Attention: Learning Reliability-Aware Representations for Vision Transformers](https://mlsanity.com/paper/2508.08547/) (2025)

## Abstract (arXiv)

Model calibration seeks to ensure that models produce confidence scores that accurately reflect the true likelihood of their predictions being correct. However, existing calibration approaches are fundamentally tied to datasets of one-hot labels implicitly assuming full certainty in all the annotations. Such datasets are effective for classification but provides insufficient knowledge of uncertainty for model calibration, necessitating the curation of datasets with numerically rich ground-truth confidence values. However, due to the scarcity of uncertain visual examples, such samples are not easily available as real datasets. In this paper, we introduce calibration-aware data augmentation to create synthetic datasets of diverse samples and their ground-truth uncertainty. Specifically, we present Calibration-aware Semantic Mixing (CSM), a novel framework that generates training samples with mixed class characteristics and annotates them with distinct confidence scores via diffusion models. Based on this framework, we propose calibrated reannotation to tackle the misalignment between the annotated confidence score and the mixing ratio during the diffusion reverse process. Besides, we explore the loss functions that better fit the new data representation paradigm. Experimental results demonstrate that CSM achieves superior calibration compared to the state-of-the-art calibration approaches. Our code is hrefhttps://github.com/E-Galois/CSMavailable here.