Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Survival Tree01:19

Survival Tree

172
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
 Building a Survival Tree
Constructing a...
172
Difference from Background: Limit of Detection01:05

Difference from Background: Limit of Detection

7.2K
The limit of detection (LOD) is the smallest amount of analyte that can be distinguished from the background noise. The LOD value corresponds to the concentration at which the analyte signal is three times larger than the standard deviation of the blank signal. Below this value, the analyte signal cannot be differentiated from the background noise. It is calculated by dividing the calibration slope by 3 times the standard deviation of the blank signals.
The LOD indicates the presence or absence...
7.2K
Reducing Line Loss01:18

Reducing Line Loss

209
In a three-phase circuit, line loss is an indicator of energy dissipated as heat due to the resistance of transmission lines. To address this, incorporating transformers into the system—a step-up transformer at the source and a step-down transformer at the load—is a strategic solution. Two three-phase transformers are introduced to improve this.
With a step-up transformer at the source, the voltage is increased, thereby reducing the current in the transmission lines since power loss...
209
Margin of Error01:27

Margin of Error

4.6K
The margin of error is also called the maximum error of an estimate. The margin of error is the maximum possible or expected difference between the observed sample parameter value and the actual population parameter value. For proportion, it is the maximum difference between the value of sample proportion obtained from the data and the true value of population proportion. As the true value of the population parameter is not known, the margin of error is calculated using the sample statistic.
4.6K
Aggregates Classification01:29

Aggregates Classification

400
Aggregate classification is generally based on its size, petrographic characteristics, weight, and source. Size classification ranges from coarse to fine aggregates, defined by the size of the particles. Coarse aggregates are particles that do not pass through ASTM sieve No. 4, and aggregates that pass through the sieve are fine aggregates.
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...
400
Predicting Products: Substitution vs. Elimination02:52

Predicting Products: Substitution vs. Elimination

12.4K
When a nucleophile and an alkyl halide react, nucleophilic substitution and β-elimination reactions compete to generate products.
The following factors can influence the mechanisms competing against each other:
12.4K

You might also read

Related Articles

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

Sort by
Same author

Comparing virus incubation time in SIRC models: Deterministic versus stochastic approaches.

Infectious Disease Modelling·2025
Same author

Parallel VMamba and Attention-Based Pneumonia Severity Prediction from CXRs: A Robust Model with Segmented Lung Replacement Augmentation.

Diagnostics (Basel, Switzerland)·2025
Same author

Annotated image dataset with different stages of European pear rust for UAV-based automated symptom detection in orchards.

Data in brief·2025
Same author

Annotated image dataset of fire blight symptoms for object detection in orchards.

Data in brief·2024
Same author

Lung pneumonia severity scoring in chest X-ray images using transformers.

Medical & biological engineering & computing·2024
Same author

COVID-19 Infection Percentage Estimation from Computed Tomography Scans: Results and Insights from the International Per-COVID-19 Challenge.

Sensors (Basel, Switzerland)·2024

Related Experiment Video

Updated: Sep 27, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

662

Deep Learning with Discriminative Margin Loss for Cross-Domain Consumer-to-Shop Clothes Retrieval.

Pendar Alirezazadeh1, Fadi Dornaika1,2,3, Abdelmalik Moujahid4

  • 1Department of Informatics, University of the Basque Country, 20008 Donostia-San Sebastian, Spain.

Sensors (Basel, Switzerland)
|April 12, 2022
PubMed
Summary

This study introduces a new Discriminative Margin Loss (DML) for improved consumer-to-shop clothes retrieval. DML enhances accuracy by learning different margins for positive and negative pairs, outperforming existing methods in fashion searches.

Keywords:
adaptive margincross-domain fashion retrievaldeep learningdiscriminative analysismargin-based loss function

More Related Videos

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.4K
Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

10.8K

Related Experiment Videos

Last Updated: Sep 27, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

662
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.4K
Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

10.8K

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Machine Learning

Background:

  • Consumer-to-shop clothes retrieval faces challenges like varied appearances, camera angles, and backgrounds, leading to low accuracy with traditional models.
  • Convolutional Neural Networks (CNNs) have improved garment retrieval, but standard softmax loss struggles with the large visual variance in fashion data.
  • Existing margin-based softmax losses (e.g., CosFace) are unsuitable for cross-domain fashion search due to uniform margins for positive and negative pairs.

Purpose of the Study:

  • To address the limitations of existing methods in consumer-to-shop clothes retrieval, particularly the handling of diverse negative pairs in the fashion domain.
  • To introduce a novel loss function, the cross-domain Discriminative Margin Loss (DML), designed to enhance the discriminative power of feature extraction for fashion retrieval.
  • To improve the accuracy and effectiveness of matching customer-taken photos with shop inventory.

Main Methods:

  • Developed and implemented the cross-domain Discriminative Margin Loss (DML), a novel loss function.
  • DML learns distinct margins for positive and negative pairs, with a larger margin for negative pairs to reduce intraclass variance.
  • Utilized CNNs for feature extraction and evaluated the DML function on publicly available fashion datasets (DARN and DeepFashion benchmarks).

Main Results:

  • The proposed DML function significantly outperforms existing loss functions in consumer-to-shop clothes retrieval tasks.
  • DML achieves state-of-the-art performance on the DARN and DeepFashion datasets for both Consumer-to-Shop and InShop Clothes Retrieval benchmarks.
  • The differential margin approach in DML effectively handles the large variability of negative pairs in fashion data.

Conclusions:

  • The cross-domain Discriminative Margin Loss (DML) is a highly effective method for improving consumer-to-shop clothes retrieval accuracy.
  • DML offers a superior solution for cross-domain fashion search by better managing intraclass variance among negative pairs.
  • This research advances the field of visual search in the fashion domain, providing a more robust and accurate retrieval system.