# Scaling of Class-wise Training Losses for Post-hoc Calibration

arXiv: https://arxiv.org/abs/2306.10989 · HTML: https://mlsanity.com/paper/2306.10989/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 34 references that are in the map.
- First posted on arXiv 19 Jun 2023.

## Builds on (most cited first, 18 of 18)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [When Does Label Smoothing Help?](https://mlsanity.com/paper/1906.02629/) (2019)
- [Deep Networks with Stochastic Depth](https://mlsanity.com/paper/1603.09382/) (2016)
- [Beyond temperature scaling: Obtaining well-calibrated multiclass probabilities with Dirichlet calibration](https://mlsanity.com/paper/1910.12656/) (2019)
- [Panoptic-DeepLab](https://mlsanity.com/paper/1910.04751/) (2019)
- [Calibrating Deep Neural Networks using Focal Loss](https://mlsanity.com/paper/2002.09437/) (2020)
- [Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect](https://mlsanity.com/paper/2009.12991/) (2020)
- [Mix-n-Match: Ensemble and Compositional Methods for Uncertainty Calibration in Deep Learning](https://mlsanity.com/paper/2003.07329/) (2020)
- [RobustScanner: Dynamically Enhancing Positional Clues for Robust Text Recognition](https://mlsanity.com/paper/2007.07542/) (2020)
- [Intra Order-preserving Functions for Calibration of Multi-Class Neural Networks](https://mlsanity.com/paper/2003.06820/) (2020)
- [Parameterized Temperature Scaling for Boosting the Expressive Power in Post-Hoc Uncertainty Calibration](https://mlsanity.com/paper/2102.12182/) (2021)
- [Meta-Cal: Well-controlled Post-hoc Calibration by Ranking](https://mlsanity.com/paper/2105.04290/) (2021)
- [Dynamic Class Queue for Large Scale Face Recognition In the Wild](https://mlsanity.com/paper/2105.11113/) (2021)

## Built on by (most cited first, 7 of 7)

- [Optimizing Calibration by Gaining Aware of Prediction Correctness](https://mlsanity.com/paper/2404.13016/) (2024)
- [h-calibration: Rethinking Classifier Recalibration with Probabilistic Error-Bounded Objective](https://mlsanity.com/paper/2506.17968/) (2025)
- [Quantile Adaptive Temperature Scaling for Confidence Calibration](https://mlsanity.com/paper/2606.21749/) (2026)
- [Towards Precise Prediction Uncertainty in GNNs: Refining GNNs with Topology-grouping Strategy](https://mlsanity.com/paper/2412.14223/) (2024)
- [Group-wise Scaling and Orthogonal Decomposition for Domain-Invariant Feature Extraction in Face Anti-Spoofing](https://mlsanity.com/paper/2507.04006/) (2025)
- [Private Federated Multiclass Post-hoc Calibration](https://mlsanity.com/paper/2510.01987/) (2025)
- [Rethinking Detection Calibration: A Coordinate and Direction Perspective](https://mlsanity.com/paper/2607.29040/) (2026)

## Abstract (arXiv)

The class-wise training losses often diverge as a result of the various levels of intra-class and inter-class appearance variation, and we find that the diverging class-wise training losses cause the uncalibrated prediction with its reliability. To resolve the issue, we propose a new calibration method to synchronize the class-wise training losses. We design a new training loss to alleviate the variance of class-wise training losses by using multiple class-wise scaling factors. Since our framework can compensate the training losses of overfitted classes with those of under-fitted classes, the integrated training loss is preserved, preventing the performance drop even after the model calibration. Furthermore, our method can be easily employed in the post-hoc calibration methods, allowing us to use the pre-trained model as an initial model and reduce the additional computation for model calibration. We validate the proposed framework by employing it in the various post-hoc calibration methods, which generally improves calibration performance while preserving accuracy, and discover through the investigation that our approach performs well with unbalanced datasets and untuned hyperparameters.