Can I read Bootstrapping the Relationship Between Images and Their Clean and Noisy Labels on EtoBox?

Bootstrapping the Relationship Between Images and Their Clean and Noisy Labels by Smart, Brandon; Carneiro, Gustavo is a scholarly article available to read on EtoBox.

What is Bootstrapping the Relationship Between Images and Their Clean and Noisy Labels about?

Many state-of-the-art noisy-label learning methods rely on learning mechanisms that estimate the samples' clean labels during training and discard their original noisy labels. However, this approach prevents the learning of the relationship between images, noisy labels and clean labels, which has been shown to be useful when dealing with instance-dependent label noise problems. Furthermore, methods that do aim to learn this relationship require cleanly annotated subsets of data, as well as distillation or multi-faceted models for training. In this paper, we propose a new training algorithm that relies on a simple model to learn the relationship between clean and noisy labels without the need for a cleanly labelled subset of data. Our algorithm follows a 3-stage process, namely: 1) self-supervised pre-training followed by an early-stopping training of the classifier to confidently predict clean labels for a subset of the training set; 2) use the clean set from stage (1) to bootstrap the relationship between images, noisy labels and clean labels, which we exploit for effective relabelling of the remaining training set using semi-supervised learning; and 3) supervised training of the

Author

Smart, Brandon; Carneiro, Gustavo

Published

2022

Language

EN