Deep Large-Margin Rank Loss for Multi-Label Image Classification

Zhongchen Ma (), Zongpeng Li and Yongzhao Zhan
Additional contact information
Zhongchen Ma: The School of Computer Science and Communications Engineering, Jiangsu University, Zhenjiang 212013, China
Zongpeng Li: The School of Computer Science and Communications Engineering, Jiangsu University, Zhenjiang 212013, China
Yongzhao Zhan: The School of Computer Science and Communications Engineering, Jiangsu University, Zhenjiang 212013, China

Mathematics, 2022, vol. 10, issue 23, 1-14

Abstract: The large-margin technique has served as the foundation of several successful theoretical and empirical results in multi-label image classification. However, most large-margin techniques are only suitable to shallow multi-label models with preset feature representations and a few large-margin techniques of neural networks only enforce margins at the output layer, which are not well suitable for deep networks. Based on the large-margin technique, a deep large-margin rank loss function suitable for any network structure is proposed, which is able to impose a margin on any chosen set of layers of a deep network, allows choosing any ℓ p norm ( p ≥ 1 ) on the metric measuring the margin between labels and is applicable to any network architecture. Although the complete computation of deep large-margin rank loss function has the O ( C 2 ) time complexity, where C denotes the size of the label set, which would cause scalability issues when C is large, a negative sampling technique was proposed to make the loss function scale linearly to C . Experimental results on two large-scale datasets, VOC2007 and MS-COCO, show that the deep large-margin ranking function improves the robustness of the model in multi-label image classification tasks while enhancing the model’s anti-noise performance.

Keywords: image classification; large-margin technique; deep neural network; robustness; anti-noise performance (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2022
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/10/23/4584/pdf (application/pdf)
https://www.mdpi.com/2227-7390/10/23/4584/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:10:y:2022:i:23:p:4584-:d:992546

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().