Signature Verification Using A "Siamese" Time Delay Neural Network

By Jane Bromley, James W. Bentz, L. Eon Bottou, Isabelle M Guyon, Yann LeCun, Cliff Moore, Eduard Säckinger, Roopak Shah. 1993

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Learning Dense Representations for Entity Retrieval (2019, background): “Dual encoder architectures have a long history (Bromley et al., 1994; Chopra et al., 2005; Yih et al., 2011), including for retrieval (Gillick et al., 2018).”
End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answering (2021, methodology): “We model the retriever as a dual-encoder network (Bromley et al., 1994), where one encoder fq encodes the question and another fd encodes the evidence document (to a vector).”
An Empirical Study of Training Self-Supervised Vision Transformers (2021, background): “Contrastive learning is commonly instantiated as some forms of Siamese networks [3].”
Exploring Simple Siamese Representation Learning (2020, background): “Siamese networks [4] are general models for comparing entities.”
Dual Contradistinctive Generative Autoencoder (2020, neutral): “Contrastive learning can be connected to metric learning [4, 9, 5].”
Deep multi-scale video prediction beyond mean square error (2015, background): “The authors in (Wang & Gupta, 2015) compete with supervised learning performance on ImageNet, by using a siamese architecture (Bromley et al., 1993) to mine positive and negative examples from patch triplets of videos in an unsupervised fashion.”
CrossTransformers: spatially-aware few-shot transfer (2020, background): “Matching-based methods [28, 75, 78, 89] instead learn representations for similarity functions [11, 16, 17, 44, 82], in the hope that the similarities will generalize to new data.”
Meta-learning with differentiable closed-form solvers (2018, background): “In a Siamese network [33, 34, 18], Λ is a nearest neighbor classifier, employing inner-products or various distance functions.”
Learning feed-forward one-shot learners (2016, background): “A different approach to one-shot learning is to learn an embedding space, which is typically done with a siamese network [2].”
Learning Deep Structure-Preserving Image-Text Embeddings (2015, background): “Finally, our work is related to deep similarity learning [4, 6, 7, 16, 18, 39, 47], though we are solving a cross-view, not a within-view, matching problem.”
Autoencoding beyond pixels using a learned similarity metric (2015, methodology): “Neural networks have been applied to metric learning in form of the Siamese architecture (Bromley et al., 1993; Chopra et al., 2005).”
Learning Image Representations Tied to Ego-Motion (2015, methodology): “The loss Le of Eq (5) is optimized by sharing the weight parameters θ among two identical stacks of layers in a “Siamese” network [2, 9, 21], as shown in the top two rows of Fig 3.”
Deep learning via semi-supervised embedding (2008, methodology): “(2) Siamese Networks (Bromley et al., 1993) are also a classical method for nonlinear embedding.”
Natural Language Inference by Tree-Based Convolution and Heuristic Matching (2015, background): “A typical neural architecture to model sentence pairs is the “Siamese” structure (Bromley et al., 1993), which involves an underlying sentence model and a matching layer to determine the relationship between two sentences.”
Recent advances in convolutional neural networks (2015, background): “is a Siamese network [150], is jointly trained in cascade with the off-the-shelf model [149].”
An overview of deep learning in medical imaging focusing on MRI (2018, background): “[81]) that’s recently been shown to enable one-shot learning, i.”