Learning from Long-Tailed Noisy Data with Sample Selection and Balanced Loss

TL;DR

This paper introduces a robust semi-supervised learning method for long-tailed noisy data that uses sample selection and a balanced loss to improve deep learning performance in real-world noisy, imbalanced datasets.

Contribution

The paper proposes a novel approach combining sample selection and a balanced loss to effectively learn from long-tailed noisy datasets, outperforming existing methods.

Findings

Outperforms state-of-the-art methods on benchmark datasets.

Effectively separates clean and noisy data for training.

Improves robustness of deep neural networks in noisy, imbalanced scenarios.

Abstract

The success of deep learning depends on large-scale and well-curated training data, while data in real-world applications are commonly long-tailed and noisy. Many methods have been proposed to deal with long-tailed data or noisy data, while a few methods are developed to tackle long-tailed noisy data. To solve this, we propose a robust method for learning from long-tailed noisy data with sample selection and balanced loss. Specifically, we separate the noisy training data into clean labeled set and unlabeled set with sample selection, and train the deep neural network in a semi-supervised manner with a balanced loss based on model bias. Extensive experiments on benchmarks demonstrate that our method outperforms existing state-of-the-art methods.