Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,291 papers · 148 categories

Trend · papers per month

237475712949 · Jun 202019922001200920182026
48 results for triplet networks

New method samples triplets from data distributions for training Triplet networks.

problem Training robust Triplet networks with discriminative triplets.
method Bayesian updating of multivariate normal distributions for dynamic class embedding sampling.
result Experimental validation on MNIST and histopathology CRC datasets shows effectiveness of the proposed method.

New method accelerates large margin metric learning for nearest neighbor classification.

problem Efficiently learning metrics for nearest neighbor classification.
method Triplet mining and stratified sampling for large margin metric learning.
result Improved efficiency and scalability of optimization.

Enhances DNN robustness with adversarial training and triplet loss.

problem Vulnerability of DNNs to adversarial examples.
method Adversarial Training with Triplet Loss (AT2^2L) incorporating triplet loss into adversarial training framework.
result Significantly improves DNN robustness without accuracy loss.

Paper introduces new loss functions for Siamese networks using FDA.

problem Training Siamese networks with improved loss functions.
method Proposes Fisher Discriminant Triplet (FDT) and Fisher Discriminant Contrastive (FDC) loss functions based on FDA.
result Shows effectiveness of FDT and FDC on MNIST and histopathology datasets.

Personalized activity recognition improves performance for diverse users.

problem Poor performance of impersonal algorithms for individual users.
method Personalized activity recognition using deep embeddings from a fully convolutional neural network with triplet loss.
result Novel subject triplet loss provides the best performance overall.

Deep Triplet Networks improve brain imaging modality recognition with limited data.

problem Efficiently recognizing new imaging modalities with scarce training data.
method Few-shot learning model based on Deep Triplet Networks.
result The model outperforms traditional CNN classifiers in modality recognition with limited data.

PerceptNet learns haptic signal similarity using human data.

problem Designing haptic icons requires accurate perceptual similarity estimation.
method Deep neural network projecting signals to an embedding space with a triplet loss.
result Our method effectively models perceptual dissimilarity compared to alternatives.

TristouNet is a neural network architecture based on Long Short-Term Memory recurrent networks, meant to project speech sequences into a fixed-dimensional euclidean space. Thanks to the triplet loss paradigm used for training, the resulting sequence embeddings can be compared directly with the euclidean distance, for s…

2016-09-14abs ↗pdf ↗

Deep learning has proven itself as a successful set of models for learning useful semantic representations of data. These, however, are mostly implicitly learned as part of a classification task. In this paper we propose the triplet network model, which aims to learn useful representations by distance comparisons. A si…

2014-12-20abs ↗pdf ↗

This paper analyzes the stability and generalization of triplet learning algorithms.

problem Lack of theoretical understanding of triplet learning's generalization performance.
method Stability analysis and high-probability generalization bounds for triplet learning algorithms.
result Established general high-probability generalization bound for triplet learning algorithms.

Paper shows how to use elementary triplets to simplify independence model operations.

problem Simplifying operations with independence models.
method Using elementary triplets to represent conditional independences.
result Elementary triplets help in various operations like finding dominant triplets and computing model unions/intersections.

The paper presents a method to compute trusted confidence bounds for LECs in CPS.

problem Non-transparent predictions of LECs make CPS safety challenging.
method Inductive Conformal Prediction (ICP) and Triplet Network architecture.
result Efficient real-time computation of trusted confidence bounds.

The paper introduces uncertainty estimates for embedding objects based on noisy triplet comparisons.

problem Learning from ordinal data without a distance metric.
method Bootstrap and Bayesian approaches to estimate uncertainty for embedding algorithms.
result Empirical uncertainty estimates are well-calibrated and useful for selecting parameters or quantifying uncertainty.

A CNN model learns complex relationships in knowledge graphs.

problem Exploring complex relationships between entities and relationships in knowledge graphs.
method A Convolutional Neural Network (CNN) is used to learn entity and relationship representations in knowledge graphs.
result The proposed model outperforms state-of-the-art models on exploring unseen relationships.

pLogicNet combines logic rules and embeddings for efficient knowledge graph reasoning.

problem Efficiently predicting missing facts in knowledge graphs.
method Combines Markov Logic Networks with knowledge graph embeddings using variational EM algorithm.
result pLogicNet outperforms traditional methods on multiple knowledge graphs.

Improves text-dependent speaker verification using neural network supervectors and AUC optimization.

problem Enhance performance in text-dependent speaker verification systems.
method Proposes a supervector generation method and AUC optimization for neural networks.
result Improves system performance through novel alignment techniques and AUC optimization.

Simple non-convex methods outperform others in ordinal embedding.

problem Finding efficient Euclidean representations of abstract items using triplet comparisons.
method Comprehensive empirical evaluation of existing algorithms and a new neural network approach.
result Simple, non-convex methods consistently outperform other algorithms.

This paper shows how optimizing with hard negative examples improves image retrieval.

problem Training with hard negative examples leads to poor training behavior.
method Characterize the space of triplets, derive why hard negatives fail, and offer a fix to the loss function.
result Optimizing with hard negative examples leads to more generalizable features and better image retrieval.

Improved cover detection in music datasets with novel triplet loss.

problem Challenging task of automatically detecting covers in audio datasets.
method Convolutional neural network mapping melodic features to embeddings, training to minimize cover distance and maximize non-cover distance.
result New prototypical triplet loss improves accuracy for large datasets and live songs.

TVAE integrates deep metric learning into VAE for better latent embedding.

problem Lack of fine-grained data representation in traditional VAE.
method TVAE combines deep metric learning with VAE, optimizing a triplet loss on VAE's mean vectors.
result TVAE achieves higher triplet accuracy (95.60%) compared to traditional VAE (75.08%).

Abstracts a construction of boundary triplets for self-adjoint elliptic problems.

problem Computing the index of families of self-adjoint elliptic boundary problems.
method Abstract axiomatic version of boundary triplets and their applications.
result Analytic proof of index theorem and computation of index differences.

We analyze the semi-hard triplet loss using Edgeworth expansion for better understanding of its behavior.

problem Understanding the behavior of the semi-hard triplet loss function.
method Developed a higher-order asymptotic analysis using the Edgeworth expansion.
result Derived explicit Edgeworth expansions revealing first-order corrections in terms of the third cumulant.

Study of symplectic trivialization and reduction of bundles with symmetry and connection.

problem Symplectic trivialization and reduction of bundles with symmetry and connection.
method Analysis of the Tulczyjew's triplet with an Ehresmann connection.
result Trivializations and reductions of iterated tangent and cotangent bundles.

Given only information in the form of similarity triplets "Object A is more similar to object B than to object C" about a data set, we propose two ways of defining a kernel function on the data set. While previous approaches construct a low-dimensional Euclidean embedding of the data set that reflects the given similar…

2016-07-28abs ↗pdf ↗

Develops a deep clustering framework for large-scale road traffic prediction.

problem Challenges in modeling diverse traffic patterns and handling high-dimensional time series with low latency.
method Combines deep clustering with CNNs and RNNs to predict road traffic at large-scale networks.
result The DeepCluster framework effectively clusters road segments and improves prediction performance.

A new method uses triplet embeddings to improve human annotation for hidden constructs.

problem Improving human annotation for hidden constructs in machine learning.
method Proposes a novel annotation approach using triplet embeddings to lift absolute annotations to relative comparisons.
result Successfully represents synthetic hidden constructs in time under noisy sampling conditions.

Paper introduces supervised and unsupervised TAM models for binary neurons.

problem Learning and retrieval of structured triplets of patterns in neural networks.
method Extends Hebbian paradigm to supervised and unsupervised protocols, using glassy statistical mechanical techniques.
result Obtained self-consistency equations for critical dataset sizes and retrieval performance.

InfoTuple efficiently selects larger tuple queries for ranking multiple objects, improving efficiency and consistency.

problem Efficiently selecting and ranking multiple objects for similarity learning.
method Adaptive selection method using mutual information maximization.
result InfoTuple outperforms state-of-the-art methods on synthetic and human response datasets.

OLÉ simplifies deep learning by enforcing class orthogonality.

problem Training deep networks for image classification without enforcing intra-class similarity and inter-class margin.
method OLÉ collapses class features into a learned subspace and pushes subspaces to be orthogonal.
result OLÉ improves classification performance and robustness.