# Rethinking Soft Label in Label Distribution Learning Perspective

arXiv: https://arxiv.org/abs/2301.13444 · HTML: https://mlsanity.com/paper/2301.13444/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 34 of its 42 references that are in the map.
- First posted on arXiv 31 Jan 2023.

## Builds on (most cited first, 30 of 34)

- [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)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [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)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer](https://mlsanity.com/paper/1612.03928/) (2016)
- [When Does Label Smoothing Help?](https://mlsanity.com/paper/1906.02629/) (2019)
- [Relational Knowledge Distillation](https://mlsanity.com/paper/1904.05068/) (2019)
- [Contrastive Representation Distillation](https://mlsanity.com/paper/1910.10699/) (2019)
- [Born Again Neural Networks](https://mlsanity.com/paper/1805.04770/) (2018)
- [Deep Layer Aggregation](https://mlsanity.com/paper/1707.06484/) (2017)
- [What Makes Training Multi-Modal Classification Networks Hard?](https://mlsanity.com/paper/1905.12681/) (2019)
- [On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networks](https://mlsanity.com/paper/1905.11001/) (2019)
- [Regularizing Class-wise Predictions via Self-knowledge Distillation](https://mlsanity.com/paper/2003.13964/) (2020)
- [Knowledge Distillation Meets Self-Supervision](https://mlsanity.com/paper/2006.07114/) (2020)
- [Improving model calibration with accuracy versus uncertainty optimization](https://mlsanity.com/paper/2012.07923/) (2020)
- [Rethinking Soft Labels for Knowledge Distillation: A Bias-Variance Tradeoff Perspective](https://mlsanity.com/paper/2102.00650/) (2021)
- [Deep Label Distribution Learning with Label Ambiguity](https://mlsanity.com/paper/1611.01731/) (2016)
- [Data Augmentation using Random Image Cropping and Patching for Deep CNNs](https://mlsanity.com/paper/1811.09030/) (2018)
- [The Effects of Regularization and Data Augmentation are Class Dependent](https://mlsanity.com/paper/2204.03632/) (2022)
- [Peer Collaborative Learning for Online Knowledge Distillation](https://mlsanity.com/paper/2006.04147/) (2020)
- [Is Label Smoothing Truly Incompatible with Knowledge Distillation: An Empirical Study](https://mlsanity.com/paper/2104.00676/) (2021)
- [Instance-Dependent Partial Label Learning](https://mlsanity.com/paper/2110.12911/) (2021)

## Abstract (arXiv)

The primary goal of training in early convolutional neural networks (CNN) is the higher generalization performance of the model. However, as the expected calibration error (ECE), which quantifies the explanatory power of model inference, was recently introduced, research on training models that can be explained is in progress. We hypothesized that a gap in supervision criteria during training and inference leads to overconfidence, and investigated that performing label distribution learning (LDL) would enhance the model calibration in CNN training. To verify this assumption, we used a simple LDL setting with recent data augmentation techniques. Based on a series of experiments, the following results are obtained: 1) State-of-the-art KD methods significantly impede model calibration. 2) Training using LDL with recent data augmentation can have excellent effects on model calibration and even in generalization performance. 3) Online LDL brings additional improvements in model calibration and accuracy with long training, especially in large-size models. Using the proposed approach, we simultaneously achieved a lower ECE and higher generalization performance for the image classification datasets CIFAR10, 100, STL10, and ImageNet. We performed several visualizations and analyses and witnessed several interesting behaviors in CNN training with the LDL.