On the Resistance of Neural Nets to Label Noise

03/30/2018
by   Amnon Drory, et al.
0

We investigate the behavior of convolutional neural networks (CNN) in the presence of label noise. We show empirically that CNN prediction for a given test sample depends on the labels of the training samples in its local neighborhood. This is similar to the way that the K-nearest neighbors (K-NN) classifier works. With this understanding, we derive an analytical expression for the expected accuracy of a K-NN, and hence a CNN, classifier for any level of noise. In particular, we show that K-NN, and CNN, are resistant to label noise that is randomly spread across the training set, but are very sensitive to label noise that is concentrated. Experiments on real datasets validate our analytical expression by showing that they match the empirical results for varying degrees of label noise.

READ FULL TEXT
04/29/2018

Local Learning with Deep and Handcrafted Features for Facial Expression Recognition

We present an approach that combines automatic features learned by convo...
05/27/2019

Combating Label Noise in Deep Learning Using Abstention

We introduce a novel method to combat label noise when training deep neu...
07/03/2019

Supervised Classifiers for Audio Impairments with Noisy Labels

Voice-over-Internet-Protocol (VoIP) calls are prone to various speech im...
07/20/2021

kNet: A Deep kNN Network To Handle Label Noise

Deep Neural Networks require large amounts of labeled data for their tra...
09/26/2013

Boosting in the presence of label noise

Boosting is known to be sensitive to label noise. We studied two approac...
03/16/2020

Neighborhood-based Pooling for Population-level Label Distribution Learning

Supervised machine learning often requires human-annotated data. While a...
12/28/2021

Improving Nonparametric Classification via Local Radial Regression with an Application to Stock Prediction

For supervised classification problems, this paper considers estimating ...

Please sign up or login with your details

Forgot password? Click here to reset