Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Downsampling

Downsampling

When considering a sampled sequence with zero values between sampling instants, one can replace it by taking every N-th value of the sequence. At these integer multiples of N, the original and sampled sequences coincide. This process, known as decimation, involves extracting every N-th sample from a sequence, thereby creating a more efficient sequence.
The Fourier transform of the decimated sequence reveals a combination of scaled and shifted versions of the original spectrum. This...

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...

Upsampling

Upsampling

Managing signal sampling rates is essential in digital signal processing to maintain signal integrity. A decimated signal, characterized by a reduced frequency range due to its lower sampling rate, can be upsampled by inserting zeros between each sample. This upsampling process expands the original spectrum and introduces repeated spectral replicas at intervals dictated by the new Nyquist frequency. To refine this zero-inserted sequence, it is passed through a lowpass filter with a cutoff...

Sampling Theorem

Sampling Theorem

In signal processing, the analysis of continuous-time signals, denoted as x(t), often involves sampling techniques to convert these signals into discrete-time signals. This process is essential for digital representation and manipulation. A critical component in sampling is the train of impulses, characterized by the sampling interval and the sampling frequency. The relationship between these parameters and the original signal's properties dictates the success of the sampling process.

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

The Reporting Quality of Machine Learning Studies on Pediatric Diabetes Mellitus: Systematic Review.

Journal of medical Internet research·2024

Same journal

RETRACTED: Zhang et al. A Novel Framework for Reconstruction and Imaging of Target Scattering Centers via Wide-Angle Incidence in Radar Networks. <i>Sensors</i> 2025, <i>25</i>, 6802.

Sensors (Basel, Switzerland)·2026

Same journal

Enhancing Unsupervised Multi-Source Domain Adaptation for Person Re-Identification via Mixture of Experts and Graph-Based Relation.

Sensors (Basel, Switzerland)·2026

Same journal

Development of an Instrumented Glove for Palmar Pressure Assessment in Kayakers.

Sensors (Basel, Switzerland)·2026

Same journal

Development and Experimental Validation of an Autonomous IoT-Based Monitoring System for Real-Time Water Quality Assessment in the Amazon River.

Sensors (Basel, Switzerland)·2026

Same journal

Semi-Supervised Adversarial Learning Framework for Controller Area Network Bus Intrusion Detection.

Sensors (Basel, Switzerland)·2026

Same journal

Smart Optimization Method for Safety Signs in Innovative Manufacturing Environments Integrating Industrial Field IoT Sensors and Knowledge Graphs.

Sensors (Basel, Switzerland)·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Aug 25, 2025

Optimized Negative Staining: a High-throughput Protocol for Examining Small and Asymmetric Protein Structure by Electron Microscopy

Optimized Negative Staining: a High-throughput Protocol for Examining Small and Asymmetric Protein Structure by Electron Microscopy

Published on: August 15, 2014

Deep Metric Learning Using Negative Sampling Probability Annealing.

Gábor Kertész¹

¹John von Neumann Faculty of Informatics, Obuda University, 1034 Budapest, Hungary.

Sensors (Basel, Switzerland)

|October 14, 2022

Summary

This summary is machine-generated.

Deep metric learning relies on effective sample selection. This study introduces negative sampling probability annealing, a novel method for triplet mining, outperforming traditional techniques by dynamically switching sampling policies.

Keywords:

deep metric learning negative sampling probability annealing triplet mining triplet network

More Related Videos

Variations on Negative Stain Electron Microscopy Methods: Tools for Tackling Challenging Systems

Variations on Negative Stain Electron Microscopy Methods: Tools for Tackling Challenging Systems

Published on: February 6, 2018

Picometer-Precision Atomic Position Tracking through Electron Microscopy

Picometer-Precision Atomic Position Tracking through Electron Microscopy

Published on: July 3, 2021

Related Experiment Videos

Last Updated: Aug 25, 2025

Optimized Negative Staining: a High-throughput Protocol for Examining Small and Asymmetric Protein Structure by Electron Microscopy

Optimized Negative Staining: a High-throughput Protocol for Examining Small and Asymmetric Protein Structure by Electron Microscopy

Published on: August 15, 2014

Variations on Negative Stain Electron Microscopy Methods: Tools for Tackling Challenging Systems

Variations on Negative Stain Electron Microscopy Methods: Tools for Tackling Challenging Systems

Published on: February 6, 2018

Picometer-Precision Atomic Position Tracking through Electron Microscopy

Picometer-Precision Atomic Position Tracking through Electron Microscopy

Published on: July 3, 2021

Area of Science:

Machine Learning
Computer Vision

Background:

Deep metric learning performance is highly dependent on input sample selection.
Triplet mining, crucial for triplet networks, involves selecting anchor, positive, and negative pairs.
Negative sample selection is complex due to numerous possibilities and its impact on triplet loss.

Purpose of the Study:

To introduce a novel negative sampling strategy called negative sampling probability annealing.
To dynamically switch sampling policies to leverage the strengths of various negative mining approaches.
To improve the effectiveness of deep metric learning through enhanced triplet mining.

Main Methods:

Developed a novel negative sampling solution based on dynamic policy switching.
Implemented negative sampling probability annealing for triplet mining.
Validated results on a synthetic dataset using cluster-analysis methods.
Measured discriminative abilities on real-life data.

Main Results:

The proposed negative sampling probability annealing method aims to combine the benefits of different mining techniques.
Experimental validation on a synthetic dataset using cluster analysis confirmed the approach's effectiveness.
The method demonstrated strong discriminative abilities when tested on real-world data.

Conclusions:

Negative sampling probability annealing offers a promising new direction for optimizing deep metric learning.
Dynamic policy switching in negative sampling can enhance model performance.
The approach shows potential for improving feature representation learning in various applications.