ExpertNet: Adversarial Learning and Recovery Against Noisy Labels

by   Amirmasoud Ghiassi, et al.

Today's available datasets in the wild, e.g., from social media and open platforms, present tremendous opportunities and challenges for deep learning, as there is a significant portion of tagged images, but often with noisy, i.e. erroneous, labels. Recent studies improve the robustness of deep models against noisy labels without the knowledge of true labels. In this paper, we advocate to derive a stronger classifier which proactively makes use of the noisy labels in addition to the original images - turning noisy labels into learning features. To such an end, we propose a novel framework, ExpertNet, composed of Amateur and Expert, which iteratively learn from each other. Amateur is a regular image classifier trained by the feedback of Expert, which imitates how human experts would correct the predicted labels from Amateur using the noise pattern learnt from the knowledge of both the noisy and ground truth labels. The trained Amateur and Expert proactively leverage the images and their noisy labels to infer image classes. Our empirical evaluations on noisy versions of CIFAR-10, CIFAR-100 and real-world data of Clothing1M show that the proposed model can achieve robust classification against a wide range of noise ratios and with as little as 20-50 models that solely focus on distilling the impact of noisy labels.



There are no comments yet.


page 1

page 2

page 3

page 4


PARS: Pseudo-Label Aware Robust Sample Selection for Learning with Noisy Labels

Acquiring accurate labels on large-scale datasets is both time consuming...

End-to-End Learning from Noisy Crowd to Supervised Machine Learning Models

Labeling real-world datasets is time consuming but indispensable for sup...

A Committee of Convolutional Neural Networks for Image Classication in the Concurrent Presence of Feature and Label Noise

Image classification has become a ubiquitous task. Models trained on goo...

Noise-resistant Deep Metric Learning with Ranking-based Instance Selection

The existence of noisy labels in real-world data negatively impacts the ...

Handling Noisy Labels via One-Step Abductive Multi-Target Learning

Learning from noisy labels is an important concern because of the lack o...

One-Step Abductive Multi-Target Learning with Diverse Noisy Samples

One-step abductive multi-target learning (OSAMTL) was proposed to handle...

Human-Guided Learning of Column Networks: Augmenting Deep Learning with Advice

Recently, deep models have been successfully applied in several applicat...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.