ExpertNet: Adversarial Learning and Recovery Against Noisy Labels

07/10/2020
by   Amirmasoud Ghiassi, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/02/2023

In Quest of Ground Truth: Learning Confident Models and Estimating Uncertainty in the Presence of Annotator Noise

The performance of the Deep Learning (DL) models depends on the quality ...
research
11/08/2022

Learning advisor networks for noisy image classification

In this paper, we introduced the novel concept of advisor network to add...
research
11/13/2020

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

Labeling real-world datasets is time consuming but indispensable for sup...
research
04/19/2020

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...
research
10/18/2022

CNT (Conditioning on Noisy Targets): A new Algorithm for Leveraging Top-Down Feedback

We propose a novel regularizer for supervised learning called Conditioni...
research
03/30/2021

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

The existence of noisy labels in real-world data negatively impacts the ...
research
11/25/2020

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

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

Please sign up or login with your details

Forgot password? Click here to reset