Please use this identifier to cite or link to this item:
Title: Label propagation via local geometry preserving for deep semi-supervised image recognition
Authors: Qing, Yuanyuan
Zeng, Yijie
Huang, Guang-Bin
Keywords: Engineering::Electrical and electronic engineering
Issue Date: 2021
Source: Qing, Y., Zeng, Y. & Huang, G. (2021). Label propagation via local geometry preserving for deep semi-supervised image recognition. Neural Networks, 143, 303-313.
Journal: Neural networks
Abstract: In this paper, we propose a novel transductive pseudo-labeling based method for deep semi-supervised image recognition. Inspired from the superiority of pseudo labels inferred by label propagation compared with those inferred from network, we argue that information flow from labeled data to unlabeled data should be kept noiseless and with minimum loss. Previous research works use scarce labeled data for feature learning and solely consider the relationship between two feature vectors to construct the similarity graph in feature space, which causes two problems that ultimately lead to noisy and incomplete information flow from labeled data to unlabeled data. The first problem is that the learned feature mapping is highly likely to be biased and can easily over-fit noise. The second problem is the loss of local geometry information in feature space during label propagation. Accordingly, we firstly propose to incorporate self-supervised learning into feature learning for cleaner information flow in feature space during subsequent label propagation. Secondly, we propose to use reconstruction concept to measure pairwise similarity in feature space, such that local geometry information can be preserved. Ablation study confirms synergistic effects from features learned with self-supervision and similarity graph with local geometry preserving. Extensive experiments conducted on benchmark datasets have verified the effectiveness of our proposed method.
ISSN: 0893-6080
DOI: 10.1016/j.neunet.2021.06.007
Schools: School of Electrical and Electronic Engineering 
Rights: © 2021 Elsevier Ltd. All rights reserved.
Fulltext Permission: none
Fulltext Availability: No Fulltext
Appears in Collections:EEE Journal Articles

Citations 50

Updated on Nov 26, 2023

Web of ScienceTM
Citations 50

Updated on Oct 29, 2023

Page view(s)

Updated on Dec 1, 2023

Google ScholarTM




Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.