# Granular-ball Representation Learning for Deep CNN on Learning with Label Noise

arXiv: https://arxiv.org/abs/2409.03254 · HTML: https://mlsanity.com/paper/2409.03254/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 42 references that are in the map.
- First posted on arXiv 5 Sep 2024.

## Builds on (most cited first, 27 of 27)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels](https://mlsanity.com/paper/1804.06872/) (2018)
- [Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels](https://mlsanity.com/paper/1805.07836/) (2018)
- [Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach](https://mlsanity.com/paper/1609.03683/) (2016)
- [MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels](https://mlsanity.com/paper/1712.05055/) (2017)
- [Object Detection in 20 Years: A Survey](https://mlsanity.com/paper/1905.05055/) (2019)
- [Normalized Loss Functions for Deep Learning with Noisy Labels](https://mlsanity.com/paper/2006.13554/) (2020)
- [Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotations](https://mlsanity.com/paper/2110.12088/) (2021)
- [Learning from Noisy Labels with Distillation](https://mlsanity.com/paper/1703.02391/) (2017)
- [CurriculumNet: Weakly Supervised Learning from Large-Scale Web Images](https://mlsanity.com/paper/1808.01097/) (2018)
- [BOND: BERT-Assisted Open-Domain Named Entity Recognition with Distant Supervision](https://mlsanity.com/paper/2006.15509/) (2020)
- [Distantly-Supervised Named Entity Recognition with Noise-Robust Learning and Language Model Augmented Self-Training](https://mlsanity.com/paper/2109.05003/) (2021)
- [Improving Generalization by Controlling Label-Noise Information in Neural Network Weights](https://mlsanity.com/paper/2002.07933/) (2020)
- [An Efficient and Adaptive Granular-ball Generation Method in Classification Problem](https://mlsanity.com/paper/2201.04343/) (2022)
- [Learning Deep Networks from Noisy Labels with Dropout Regularization](https://mlsanity.com/paper/1705.03419/) (2017)
- [An Effective Label Noise Model for DNN Text Classification](https://mlsanity.com/paper/1903.07507/) (2019)
- [On Learning Contrastive Representations for Learning with Noisy Labels](https://mlsanity.com/paper/2203.01785/) (2022)
- [When Noisy Labels Meet Long Tail Dilemmas: A Representation Calibration Method](https://mlsanity.com/paper/2211.10955/) (2022)
- [Auxiliary Image Regularization for Deep CNNs with Noisy Labels](https://mlsanity.com/paper/1511.07069/) (2015)
- [FedDiv: Collaborative Noise Filtering for Federated Learning with Noisy Labels](https://mlsanity.com/paper/2312.12263/) (2023)
- [Attend in groups: a weakly-supervised deep learning framework for learning from web data](https://mlsanity.com/paper/1611.09960/) (2016)
- [A Unified Granular-ball Learning Model of Pawlak Rough Set and Neighborhood Rough Set](https://mlsanity.com/paper/2201.03349/) (2022)
- [Semi-Automatic Data Annotation guided by Feature Space Projection](https://mlsanity.com/paper/2007.13689/) (2020)
- [Improving Distantly-Supervised Named Entity Recognition with Self-Collaborative Denoising Learning](https://mlsanity.com/paper/2110.04429/) (2021)
- [Learning Adaptive Loss for Robust Learning with Noisy Labels](https://mlsanity.com/paper/2002.06482/) (2020)
- [Towards Robustness to Label Noise in Text Classification via Noise Modeling](https://mlsanity.com/paper/2101.11214/) (2021)

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

- [Graph Coarsening via Supervised Granular-Ball for Scalable Graph Neural Network Training](https://mlsanity.com/paper/2412.13842/) (2024)
- [3DGBGS: 3D Granular Ball Gaussian Splatting for Compact Novel View Synthesis](https://mlsanity.com/paper/2607.26578/) (2026)

## Abstract (arXiv)

In actual scenarios, whether manually or automatically annotated, label noise is inevitably generated in the training data, which can affect the effectiveness of deep CNN models. The popular solutions require data cleaning or designing additional optimizations to punish the data with mislabeled data, thereby enhancing the robustness of models. However, these methods come at the cost of weakening or even losing some data during the training process. As we know, content is the inherent attribute of an image that does not change with changes in annotations. In this study, we propose a general granular-ball computing (GBC) module that can be embedded into a CNN model, where the classifier finally predicts the label of granular-ball (gb) samples instead of each individual samples. Specifically, considering the classification task: (1) in forward process, we split the input samples as gb samples at feature-level, each of which can correspond to multiple samples with varying numbers and share one single label; (2) during the backpropagation process, we modify the gradient allocation strategy of the GBC module to enable it to propagate normally; and (3) we develop an experience replay policy to ensure the stability of the training process. Experiments demonstrate that the proposed method can improve the robustness of CNN models with no additional data or optimization.