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

TL;DR

This paper introduces a granular-ball computing module for CNNs that enhances robustness against label noise by aggregating samples into granular-balls, avoiding data loss and additional optimization.

Contribution

The study proposes a novel GBC module that predicts labels at the granular-ball level, improving robustness to label noise without extra data or complex optimizations.

Findings

Improves CNN robustness to label noise

No additional data or optimization needed

Maintains training stability with experience replay

Abstract

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.