Self-semi-supervised Learning to Learn from NoisyLabeled Data

TL;DR

This paper introduces a novel approach combining self-semi-supervised learning with improved noisy label differentiation to enhance training robustness on datasets with label noise, reducing reliance on perfectly labeled data.

Contribution

It proposes a new method that more accurately identifies clean versus noisy labels and leverages self-semi-supervised learning to improve model training with noisy data.

Findings

Enhanced differentiation of clean and noisy labels.

Improved model robustness to label noise.

Effective semi-supervised training on noisy datasets.

Abstract

The remarkable success of today's deep neural networks highly depends on a massive number of correctly labeled data. However, it is rather costly to obtain high-quality human-labeled data, leading to the active research area of training models robust to noisy labels. To achieve this goal, on the one hand, many papers have been dedicated to differentiating noisy labels from clean ones to increase the generalization of DNN. On the other hand, the increasingly prevalent methods of self-semi-supervised learning have been proven to benefit the tasks when labels are incomplete. By 'semi' we regard the wrongly labeled data detected as un-labeled data; by 'self' we choose a self-supervised technique to conduct semi-supervised learning. In this project, we designed methods to more accurately differentiate clean and noisy labels and borrowed the wisdom of self-semi-supervised learning to train noisy labeled data.