A Survey on Applications of Siamese Neural Networks in Computer Vision

Nandy, Abhilash; Haldar, Sushovan; Banerjee, Subhashis; Mitra, Sukanya

doi:10.1109/incet49848.2020.9153977

Cited by 23 publications

(13 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, Koch et al [49] used the weighted L1 distance and a variation of binary cross entropy as a loss function (Equation 5). Besides, Nandy et al [51] highlighted the L1 and L2 as examples of relevant similarity functions. Chopra et al [52] used the Euclidian distance (L2) and Contrastive Loss (Equation 6) as similarity functions.…”

Section: Similarity and Loss Functionsmentioning

confidence: 99%

Siamese Convolutional Neural Network for Heartbeat Classification Using Limited 12-Lead ECG Datasets

et al. 2023

View full text Add to dashboard Cite

The Electrocardiogram (ECG) is a low-cost exam commonly used to diagnose abnormalities in the cardiac cycle. Over the years, the scientific community has investigated the automatic classification of ECG signals driven by advanced Machine Learning (ML) techniques. Despite recent scientific advances, annotating large and diverse datasets to support the training of ML techniques is still very time-consuming and error-prone. Indeed, ML techniques whose training does not require extensive and well-annotated datasets are becoming even more prominent. Therefore, it is possible to correctly identify and classify abnormalities in the cardiac cycle (e.g., rare cardiologic disturbs) using limited data available in ECG datasets. However, the classification of heartbeats from digital tracings of ECG signals containing 12 leads from imbalanced datasets is challenging due to many existing heart diseases. This study investigates the few-shot learning paradigm based on Siamese Convolutional Neural Networks (SCNN), popular in imaging classification problems, to classify 12-Lead ECG heartbeats using a few training samples with supervised information. The proposed SCNN model presented an accuracy of up to 95% in a public dataset based on the hold-out validation method, implemented for different combinations of similarity and loss functions. Besides, using the 7-fold cross-validation method, the model presented a mean area under the curve of 89%. We also compared the class-by-class classification results with those of similar methods available in the literature, obtaining the same or better results based on performance metrics such as accuracy, precision, recall, and specificity.

show abstract

Section: Similarity and Loss Functionsmentioning

confidence: 99%

Siamese Convolutional Neural Network for Heartbeat Classification Using Limited 12-Lead ECG Datasets

et al. 2023

View full text Add to dashboard Cite

show abstract

“…The idea is that the siamese network learn how to extract feature vectors from the instances in a way these vectors are close if the instances are similar and these vectors are far if not. SNNs are in general computationally expensive but perform better as compared to other techniques when learning similarity [29].…”

Section: Siamese Neural Networkmentioning

confidence: 99%

Graph-Based Siamese Network for Authorship Verification

et al. 2022

View full text Add to dashboard Cite

In this work, we propose a novel approach to solve the authorship identification task on a cross-topic and open-set scenario. Authorship verification is the task of determining whether or not two texts were written by the same author. We model the documents in a graph representation and then a graph neural network extracts relevant features from these graph representations. We present three strategies to represent the texts as graphs based on the co-occurrence of the POS labels of words. We propose a Siamese Network architecture composed of graph convolutional networks along with pooling and classification layers. We present different variants of the architecture and discuss the performance of each one. To evaluate our approach we used a collection of fanfiction texts provided by the PAN@CLEF 2021 shared task in two settings: a “small” corpus and a “large” corpus. Our graph-based approach achieved average scores (AUC ROC, F1, Brier score, F0.5u, and C@1) between 90% and 92.83% when training on the “small” and “large” corpus, respectively. Our model obtain results comparable to those of the state of the art in this task and greater than traditional baselines.

show abstract

“…As of 2022, several analytical reviews involving Siamese and triplet neural networks [1][2][3][4] have been published. In [1], a wide range of works (164 references) on the Siamese neural networks' application in different fields of science and technology are mentioned.…”

Section: Related Workmentioning

confidence: 99%

“…In the review, ref. [3], the general principles of Siamese and triplet neural networks used in computer vision, as well as their performance on the selected datasets, are considered. The main advantages of triplet networks are shown to simplify data preprocessing (normalization and calibration).…”

Section: Related Workmentioning

confidence: 99%

A Survey on Symmetrical Neural Network Architectures and Applications

et al. 2022

View full text Add to dashboard Cite

A number of modern techniques for neural network training and recognition enhancement are based on their structures’ symmetry. Such approaches demonstrate impressive results, both for recognition practice, and for understanding of data transformation processes in various feature spaces. This survey examines symmetrical neural network architectures—Siamese and triplet. Among a wide range of tasks having various mathematical formulation areas, especially effective applications of symmetrical neural network architectures are revealed. We systematize and compare different architectures of symmetrical neural networks, identify genetic relationships between significant studies of different authors’ groups, and discuss opportunities to improve the element base of such neural networks. Our survey builds bridges between a large number of isolated studies with significant practical results in the considered area of knowledge, so that the presented survey acquires additional relevance.

show abstract

A Survey on Applications of Siamese Neural Networks in Computer Vision

Cited by 23 publications

References 16 publications

Siamese Convolutional Neural Network for Heartbeat Classification Using Limited 12-Lead ECG Datasets

Siamese Convolutional Neural Network for Heartbeat Classification Using Limited 12-Lead ECG Datasets

Graph-Based Siamese Network for Authorship Verification

A Survey on Symmetrical Neural Network Architectures and Applications

Contact Info

Product

Resources

About