Image classification with deep learning in the presence of noisy labels: A survey

Date

2021-03-01

Author

Algan, Gorkem
Ulusoy, İlkay

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

227
views

0
downloads

Image classification systems recently made a giant leap with the advancement of deep neural networks. However, these systems require an excessive amount of labeled data to be adequately trained. Gathering a correctly annotated dataset is not always feasible due to several factors, such as the expensiveness of the labeling process or difficulty of correctly classifying data, even for the experts. Because of these practical challenges, label noise is a common problem in real-world datasets, and numerous methods to train deep neural networks with label noise are proposed in the literature. Although deep neural networks are known to be relatively robust to label noise, their tendency to overfit data makes them vulnerable to memorizing even random noise. Therefore, it is crucial to consider the existence of label noise and develop counter algorithms to fade away its adverse effects to train deep neural networks efficiently. Even though an extensive survey of machine learning techniques under label noise exists, the literature lacks a comprehensive survey of methodologies centered explicitly around deep learning in the presence of noisy labels. This paper aims to present these algorithms while categorizing them into one of the two subgroups: noise model based and noise model free methods. Algorithms in the first group aim to estimate the noise structure and use this information to avoid the adverse effects of noisy labels. Differently, methods in the second group try to come up with inherently noise robust algorithms by using approaches like robust losses, regularizers or other learning paradigms. (C) 2021 Elsevier B.V. All rights reserved.

URI

https://hdl.handle.net/11511/93880

Journal

KNOWLEDGE-BASED SYSTEMS

DOI

https://doi.org/10.1016/j.knosys.2021.106771

Collections

Department of Electrical and Electronics Engineering, Article

Suggestions

OpenMETU
Core

Deep Learning in the Presence of Label Noise: A Meta-Learning Approach Algan, Görkem; Ulusoy, İlkay; Department of Electrical and Electronics Engineering (2021-3-12) Image classification systems recently made a giant leap with the advancement of deep neural networks. However, these systems require an excessive amount of labeled data to be adequately trained. Gathering a correctly annotated dataset is not always feasible due to practical challenges. Because of these practical challenges, label noise is a common problem in real-world datasets. This thesis presents two novel label noise robust learning algorithms: MSLG (Meta Soft Label Generation) and MetaLabelNet. Both al...
Image compression method based on learned lifting-based dwt and learned zerotree-like entropy model Şahin, Uğur Berk; Kamışlı, Fatih; Department of Electrical and Electronics Engineering (2022-8) The success of deep learning in computer vision has sparked great interest in investigating deep learning-based algorithms also in many image processing applications, including image compression. The most popular end-to-end learned image compression approaches are based on auto-encoder architectures, where the image is mapped via convolutional neural networks (CNNs) into a transform (latent) representation that is quantized and processed again with CNNs to obtain the reconstructed image. The quantized laten...
Position estimation for timing belt drives of precision machinery using structured neural networks KILIÇ, Ergin; DOĞRUER, CAN ULAŞ; Dölen, Melik; Koku, Ahmet Buğra (2012-05-01) This paper focuses on a viable position estimation scheme for timing-belt drives using artificial neural networks. In this study, the position of a carriage (load) is calculated via a structured neural network topology accepting input from a position sensor on the actuator side of the timing belt. The paper presents a detailed discussion on the source of transmission errors. The characteristics of the error in different operation regimes are exploited to construct different network topologies. That is, a re...
Representing temporal knowledge in connectionist expert systems Alpaslan, Ferda Nur (1996-09-27) This paper introduces a new temporal neural networks model which can be used in connectionist expert systems. Also, a Variation of backpropagation algorithm, called the temporal feedforward backpropagation algorithm is introduced as a method for training the neural network. The algorithm was tested using training examples extracted from a medical expert system. A series of experiments were carried out using the temporal model and the temporal backpropagation algorithm. The experiments indicated that the alg...
Image compression using random neural networks Sungur, M (1998-10-28) Random neural network is a novel pulsed neural network model which has nice analytical features. In this paper, we review the use of the random neural network for the lossy compression of digital gray level images.

Citation Formats

G. Algan and İ. Ulusoy, “Image classification with deep learning in the presence of noisy labels: A survey,” KNOWLEDGE-BASED SYSTEMS, vol. 215, pp. 0–0, 2021, Accessed: 00, 2021. [Online]. Available: https://hdl.handle.net/11511/93880.