Deep Large-Margin Rank Loss for Multi-Label Image Classification
Open Access
- 3 December 2022
- journal article
- research article
- Published by MDPI AG in Mathematics
- Vol. 10 (23), 4584
- https://doi.org/10.3390/math10234584
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 norm () 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 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
Funding Information
- National Natural Science Foundation of China (No. 62006098)
- China Postdoctoral Science Foundation (2020M681515)
This publication has 32 references indexed in Scilit:
- Deep Classifiers from Image Tags in the WildPublished by Association for Computing Machinery (ACM) ,2015
- Is object localization for free? - Weakly-supervised learning with convolutional neural networksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- The Pascal Visual Object Classes Challenge: A RetrospectiveInternational Journal of Computer Vision, 2014
- ML-KNN: A lazy learning approach to multi-label learningPattern Recognition, 2007
- Histograms of Oriented Gradients for Human DetectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004
- Learning multi-label scene classificationPattern Recognition, 2004
- A Decision-Theoretic Generalization of On-Line Learning and an Application to BoostingJournal of Computer and System Sciences, 1997
- A comparative study of texture measures with classification based on featured distributionsPattern Recognition, 1996
- Support-vector networksMachine Learning, 1995