DeepAI AI Chat
Log In Sign Up

SplitNet: Learnable Clean-Noisy Label Splitting for Learning with Noisy Labels

by   Daehwan Kim, et al.
Korea University

Annotating the dataset with high-quality labels is crucial for performance of deep network, but in real world scenarios, the labels are often contaminated by noise. To address this, some methods were proposed to automatically split clean and noisy labels, and learn a semi-supervised learner in a Learning with Noisy Labels (LNL) framework. However, they leverage a handcrafted module for clean-noisy label splitting, which induces a confirmation bias in the semi-supervised learning phase and limits the performance. In this paper, we for the first time present a learnable module for clean-noisy label splitting, dubbed SplitNet, and a novel LNL framework which complementarily trains the SplitNet and main network for the LNL task. We propose to use a dynamic threshold based on a split confidence by SplitNet to better optimize semi-supervised learner. To enhance SplitNet training, we also present a risk hedging method. Our proposed method performs at a state-of-the-art level especially in high noise ratio settings on various LNL benchmarks.


Reliable Label Correction is a Good Booster When Learning with Extremely Noisy Labels

Learning with noisy labels has aroused much research interest since data...

Bootstrapping the Relationship Between Images and Their Clean and Noisy Labels

Many state-of-the-art noisy-label learning methods rely on learning mech...

CrossSplit: Mitigating Label Noise Memorization through Data Splitting

We approach the problem of improving robustness of deep learning algorit...

Knockoffs-SPR: Clean Sample Selection in Learning with Noisy Labels

A noisy training set usually leads to the degradation of the generalizat...

SemiNLL: A Framework of Noisy-Label Learning by Semi-Supervised Learning

Deep learning with noisy labels is a challenging task. Recent prominent ...

Towards the Identifiability in Noisy Label Learning: A Multinomial Mixture Approach

Learning from noisy labels plays an important role in the deep learning ...

Decoupling Representation and Classifier for Noisy Label Learning

Since convolutional neural networks (ConvNets) can easily memorize noisy...