Please use this identifier to cite or link to this item: https://hdl.handle.net/20.500.13087/563
Title: Semi-supervised robust deep neural networks for multi-label image classification
Authors: Çevikalp, Hakan
Benligiray, Burak
Gerek, Ömer Nezih
Keywords: Multi-label classification
Semi-supervised learning
Ramp loss
Image classification
Deep learning
Issue Date: 2020
Publisher: Elsevier Sci Ltd
Abstract: This paper introduces a robust method for semi-supervised training of deep neural networks for multi-label image classification. To this end, a ramp loss is utilized since it is more robust against noisy and incomplete image labels compared to the classic hinge loss. The proposed method allows for learning from both labeled and unlabeled data in a semi-supervised setting. This is achieved by propagating labels from the labeled images to their unlabeled neighbors in the feature space. Using a robust loss function becomes crucial here, as the initial label propagations may include many errors, which degrades the performance of non-robust loss functions. In contrast, the proposed robust ramp loss restricts extreme penalties from the samples with incorrect labels, and the label assignment improves in each iteration and contributes to the learning process. The proposed method achieves state-of-the-art results in semi-supervised learning experiments on the CIFAR-10 and STL-10 datasets, and comparable results to the state-of the-art in supervised learning experiments on the NUS-WIDE and MS-COCO datasets. Experimental results also verify that our proposed method is more robust against noisy image labels as expected. (C) 2019 Elsevier Ltd. All rights reserved.
URI: https://doi.org/10.1016/j.patcog.2019.107164
https://hdl.handle.net/20.500.13087/563
ISSN: 0031-3203
1873-5142
Appears in Collections:Elektrik-Elektronik Mühendisliği Bölümü Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu
WoS İndeksli Yayınlar Koleksiyonu

Show full item record

CORE Recommender

WEB OF SCIENCETM
Citations

20
checked on Jun 22, 2022

Page view(s)

16
checked on Oct 3, 2022

Google ScholarTM

Check

Altmetric


Items in GCRIS Repository are protected by copyright, with all rights reserved, unless otherwise indicated.