Jove
Visualize
Contact Us

Related Concept Videos

Transformers01:26

Transformers

1.7K
A device that transforms voltages from one value to another using induction is called a transformer. A transformer consists of two separate coils, or windings, wrapped around the same soft iron core. However, they are electrically insulated from each other.
The iron core has a substantial relative permeability. Therefore, the magnetic field lines generated due to the current in one winding are almost entirely confined within the core, such that the same magnetic flux permeates each turn of both...
1.7K
Types Of Transformers01:16

Types Of Transformers

1.4K
Transformers can provide desired voltages to a circuit by modifying the number of turns in the secondary windings.
If the ratio of the number of turns in the secondary winding to that of the primary winding is greater than one, then the transformer is said to be a step-up transformer. In a step-up transformer, the voltage at the secondary winding is greater than the voltage applied at the primary winding.
However, if this ratio is less than one, the transformer is said to be a step-down...
1.4K
Three-Winding Transformers01:19

Three-Winding Transformers

655
Three identical single-phase transformers can be configured to form a three-phase transformer connection, which involves high-voltage and low-voltage windings. The high-voltage windings are denoted by capital letters A-B-C, while the low-voltage windings are labeled with lowercase letters a-b-c, representing their respective phases. This notation helps distinguish between the high and low voltage sides of the transformer.
In the per-unit equivalent circuit of a grounded Y-Y three-phase...
655
Inertia Tensor01:24

Inertia Tensor

1.1K
The concept of the inertia tensor is employed to depict the mass distribution and rotational inertia of a solid or rigid object. This tensor is expressed through a three-by-three matrix. Each component within this matrix corresponds to varying moments of inertia about specific axes.
The diagonal components of the inertia tensor matrix represent the moments of inertia concerning the principal axes of the object. These primary axes are defined as the axes where the object experiences the least...
1.1K
Transformers with Off-Nominal Turns Ratios01:25

Transformers with Off-Nominal Turns Ratios

491
In scenarios involving parallel transformers with disparate ratings, developing per-unit models requires accommodating off-nominal turns ratios. This situation arises when the selected base voltages are not proportional to the transformer’s voltage ratings. Consider a transformer where the rated voltages are related by the term a. If the chosen voltage bases satisfy a relationship involving term b, term c is defined as the ratio of these bases. This ratio is then substituted into the...
491
Energy Losses in Transformers01:21

Energy Losses in Transformers

1.3K
In an ideal transformer, it is assumed that there are no energy losses, and, hence, all the power at the primary winding is transferred to the secondary winding. However, in reality,  the transformers always have some energy losses, and, hence, the output power obtained at the secondary winding is less than the input power at the primary winding due to energy losses.
There are four main reasons for energy losses in transformers.
The first cause can be  the high resistance of the...
1.3K
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
  1. Home
  3. The Cur Decomposition Of Self-attention Matrices In Vision Transformers.
  1. Home
  3. The Cur Decomposition Of Self-attention Matrices In Vision Transformers.

Related Experiment Video

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

2.2K

The CUR Decomposition of Self-Attention Matrices in Vision Transformers.

Chong Wu, Maolin Che, Hong Yan

    IEEE Transactions on Pattern Analysis and Machine Intelligence
    |December 19, 2025

    View abstract on PubMed

    Summary
    This summary is machine-generated.

    We introduce CURSA, a new linear self-attention method that maintains high performance while reducing computational complexity. CURSA achieves better data efficiency, speed, and accuracy in various vision tasks compared to existing methods.

    More Related Videos

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    723

    Related Experiment Videos

    A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
    04:23

    A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

    Published on: April 21, 2023

    2.2K
    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    723

    Area of Science:

    • Computer Science
    • Artificial Intelligence
    • Machine Learning

    Background:

    • Transformers are highly successful in NLP and computer vision.
    • The self-attention mechanism is central to transformers but has quadratic complexity, limiting its use in vision.
    • Existing linear self-attention methods often compromise performance for reduced complexity.

    Purpose of the Study:

    • To propose a novel linear approximation of self-attention called CURSA.
    • To achieve both high performance and low complexity simultaneously in self-attention mechanisms.
    • To address the limitations of quadratic complexity in vision tasks.

    Main Methods:

    • Developed CURSA, a linear approximation of the vanilla self-attention mechanism.
    • Utilized CUR decomposition to break down large matrix multiplications into smaller ones.
  • Achieved nearly linear complexity through this decomposition.

    • Main Results:

    • CURSA demonstrated superior performance over state-of-the-art self-attention mechanisms.
    • Experiments in image classification, semantic segmentation, and object detection showed significant improvements.
    • CURSA achieved better data efficiency, faster processing speeds, and higher accuracy.

    Conclusions:

    • CURSA offers a promising solution for efficient and high-performing self-attention in vision tasks.
    • The method effectively balances computational complexity and model accuracy.
    • CURSA outperforms existing linear attention mechanisms across various benchmarks.