Joint dimensionality reduction and metric learning for image set classification

Yan, Wenzhu; Sun, Quansen; Sun, Huaijiang; Li, Yanmeng

doi:10.1016/j.ins.2019.12.041

Cited by 17 publications

(5 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This technology has been studied for decades and is widely used in industry, medical treatment, machine learning and other fields. In order to optimize the fusion technology, various fusion algorithms have been developed in recent years [26][27][28][29][30]. As early as in 1979, Daily et al [31] fused radar and Landsat-MSS images for the first time to extract geological information.…”

Section: Introductionmentioning

confidence: 99%

Temperature Measurement Method of Flame Image Fusion with Different Exposures

et al. 2020

View full text Add to dashboard Cite

Fixed exposure will lead to underexposure or overexposure of collected flame radiation images using CCD, which has a great influence on the temperature measuring accuracy. A temperature measurement method was proposed by image fusion with multi-exposure, which can eliminate the influence of insufficient underexposure and overexposure. The approach was first to acquire a group of flame radiation images during different exposures. Then a partial region with good exposure effect in each radiation image was obtained by segmentation, with which the complete flame image can be spliced together. An experimental system was built to calibrate the temperature measurement parameters by two-color pyrometry through a blackbody furnace. The relation between exposure time and monochromatic gray level, as well as the relation between the temperature and temperature measurement coefficient were obtained. A candle flame was selected as the measuring object and the complete and accurate flame temperature distribution was acquired following our proposed method. The experimental results show that, compared with the temperature measurement using a single exposure time, our method can effectively avoid the measurement error caused by underexposure and overexposure, and improve the measurement accuracy.

show abstract

Section: Introductionmentioning

confidence: 99%

Temperature Measurement Method of Flame Image Fusion with Different Exposures

et al. 2020

View full text Add to dashboard Cite

show abstract

“…The basic idea of supervised representation learning methods is to learn a representation which have large inter-class variations and small intra-class variations [1][3] [4]. Contrastive loss [5][6] and triplet loss [7] [8] have been widely used to capture the semantic relationship of data.…”

Section: Representation Learning For Time Seriesmentioning

confidence: 99%

A multi-level representation learning method for the classification with emerging new classes on power event monitoring data

Pan

Liu

Fan

et al. 2022

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

For the classification problem of power event monitoring data, manual rules are mainly used to recognize the known classes of events, and new classes of events cannot be extracted by using existing manual rules. But new classes may emerge with the upgrading of power equipment and traditional representation of this time series data is not proper for the task. To solve this issue, we introduce an effective approach that includes three parts: i) embed the raw object of power event in semantic space ii) learn the representation of power event with multi-level. iii) detect new classes, classify old classes, and update models to classify both new classes and old classes. Experiments on real power event monitoring dataset demonstrate that the proposed method outperforms the state-of-the-art methods.

show abstract

“…Endowed with Riemannian metric such as Stein divergence (Sra, 2012), the SPD manifold becomes the Riemannian manifold, and the geodesic distance exploits the data geometric structure more naturally than Euclidean distance (see Figure 1). Yan et al (2020) design three models to reveal the latent information across Euclidean space and Riemannian space, achieving better results in the image set classification task. Tabealhojeh et al (2023) extend the meta-learning to the Riemannian manifold, which outperforms its Euclidean counterpart.…”

Section: Introductionmentioning

confidence: 99%

“…Yan et al. (2020) design three models to reveal the latent information across Euclidean space and Riemannian space, achieving better results in the image set classification task. Tabealhojeh et al.…”

Section: Introductionmentioning

confidence: 99%

Classification of Ground‐Based Auroral Images by Learning Deep Tensor Feature Representation on Riemannian Manifold

Hu,

Zhou,

Yang

et al. 2024

Journal of Geophysical Research: Machine Learning and Computati

View full text Add to dashboard Cite

Automatically classifying a huge amount of ground‐based auroral images is essential to facilitate aurora morphology statistical research and aid in comprehending the magnetospheric dynamics. However, facing the challenge of insufficient labeled images, deep learning methods perform suboptimally on small auroral image data sets, and traditional machine learning methods based on handcrafted features heavily rely on expert knowledge. In this paper, we propose a novel method that leverages the merits of both traditional machine learning and deep learning methods by extracting deep second‐order tensor features to train a support vector machine (SVM). To improve compactness and discriminative ability of the features, we comply the intrinsic data geometry on Riemannian manifold to employ dimensionality reduction and map the dimensionality‐reduced features from Riemannian space to Euclidean space for the SVM classifier. Experimental results on small aurora data sets conclusively demonstrate the effectiveness of our method, exhibiting competitive performance with recent aurora classification methods.

show abstract

Joint dimensionality reduction and metric learning for image set classification

Cited by 17 publications

References 22 publications

Temperature Measurement Method of Flame Image Fusion with Different Exposures

Temperature Measurement Method of Flame Image Fusion with Different Exposures

A multi-level representation learning method for the classification with emerging new classes on power event monitoring data

Classification of Ground‐Based Auroral Images by Learning Deep Tensor Feature Representation on Riemannian Manifold

Contact Info

Product

Resources

About