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

Generalization, Discrimination, and Extinction01:24

Generalization, Discrimination, and Extinction

440
Generalization, discrimination, and extinction are key concepts in operant conditioning that influence how behaviors are learned and maintained.
Generalization occurs when a behavior reinforced in one context is performed in similar situations. For instance, a student who studies diligently for calculus and receives excellent grades might apply the same study habits to psychology and history, expecting similar results. Generalization shows how learning in one setting can influence behavior in...
440
Associative Learning01:27

Associative Learning

289
Associative learning is a fundamental concept in behavioral psychology, wherein a connection is established between two stimuli or events, leading to a learned response. This process is critical in understanding how behaviors are acquired and modified. Conditioning, the mechanism through which associations are formed, can be divided into two main types: classical conditioning and operant conditioning, each elucidating different aspects of associative learning.
Classical conditioning, also known...
289
Improving Translational Accuracy02:07

Improving Translational Accuracy

9.0K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
9.0K
Stereotype Content Model02:16

Stereotype Content Model

14.0K
The Stereotype Content Model (SCM) was first proposed by Susan Fiske and her colleagues (Fiske, Cuddy, Glick & Xu, 2002; see also Fiske, 2012 and Fiske, 2017). The SCM specifies that when someone encounters a new group, they will stereotype them based on two metrics: warmth—or that group’s perceived intent, and how likely they are to provide help or inflict harm—and competence—or their ability to carry out that objective. Depending on the warmth-competence...
14.0K
Residuals and Least-Squares Property01:11

Residuals and Least-Squares Property

7.3K
The vertical distance between the actual value of y and the estimated value of y. In other words, it measures the vertical distance between the actual data point and the predicted point on the line
If the observed data point lies above the line, the residual is positive, and the line underestimates the actual data value for y. If the observed data point lies below the line, the residual is negative, and the line overestimates the actual data value for y.
The process of fitting the best-fit...
7.3K
The Representativeness Heuristic02:13

The Representativeness Heuristic

15.8K
The representative heuristic describes a biased way of thinking, in which you unintentionally stereotype someone or something. For example, you may assume that your professors spend their free time reading books and engaging in intellectual conversation, because the idea of them spending their time playing volleyball or visiting an amusement park does not fit in with your stereotypes of professors.
15.8K

You might also read

Related Articles

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

Sort by
Same author

Functional and transcriptomic characterization of the receptor-like protein kinase gene GmHSL1b involved in salt stress tolerance in soybean roots.

Physiologia plantarum·2025
Same author

High-efficiency and sustainable peroxymonosulfate activation on Fe single-atom catalyst through incorporating complementary S species for enhanced water decontamination.

Journal of colloid and interface science·2025
Same author

A noncanonical role of SAT1 enables anchorage independence and peritoneal metastasis in ovarian cancer.

Nature communications·2025
Same author

Effect of Hypoglycemic Drugs on Patients with Heart Failure with or without T2DM: A Bayesian Network Meta-analysis.

Reviews in cardiovascular medicine·2025
Same author

Cuproptosis inhibits tumor progression and enhances cisplatin toxicity in ovarian cancer.

FASEB journal : official publication of the Federation of American Societies for Experimental Biology·2025
Same author

US disruptions to science could transform global research landscape.

Nature·2025

Related Experiment Video

Updated: Jun 5, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

502

Generalized zero-shot learning via discriminative and transferable disentangled representations.

Chunyu Zhang1, Zhanshan Li1

  • 1College of Computer Science and Technology, Jilin University, Changchun 130012, China; Key Laboratory of Symbolic Computation and Knowledge Engineering (Jilin University), Ministry of Education, Changchun 130012, China.

Neural Networks : the Official Journal of the International Neural Network Society
|December 10, 2024
PubMed
Summary
This summary is machine-generated.

Generalized zero-shot learning (GZSL) struggles with unseen classes. This study introduces discriminative and transferable disentangled representations (DTDR) to improve unseen sample recognition by aligning feature and semantic spaces.

Keywords:
Generalized zero-shot learningGenerative methodImage classification

More Related Videos

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

468
Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

954

Related Experiment Videos

Last Updated: Jun 5, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

502
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

468
Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

954

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Machine Learning

Background:

  • Generalized zero-shot learning (GZSL) faces challenges in recognizing unseen classes due to limited training data.
  • Existing disentanglement methods struggle with semantic consistency and independence, impacting performance on unseen data.
  • Discrepancies between visual feature representation space and semantic space, and instance interactions, are often overlooked.

Purpose of the Study:

  • To propose a novel method for learning discriminative and transferable disentangled representations (DTDR) for improved GZSL.
  • To address the limitations of existing methods in handling unseen classes and aligning representation and semantic spaces.
  • To incorporate instance-level correlations and improve the association between synthesized visual features and semantic descriptions.

Main Methods:

  • Exploiting estimated class similarities to supervise relations between seen and unseen representations.
  • Constraining similarities between semantic-matched representations using cosine similarities of semantic descriptions.
  • Reconstructing synthesized visual features to corresponding semantic descriptions for better association learning.
  • Incorporating instance-level correlations during representation learning.

Main Results:

  • The proposed DTDR method demonstrates significant improvements in generalized zero-shot learning.
  • The approach effectively bridges the gap between seen and unseen class recognition.
  • Experimental results on four datasets validate the effectiveness of the DTDR method.

Conclusions:

  • The DTDR method enhances generalized zero-shot learning by learning more discriminative and transferable representations.
  • Aligning representation and semantic spaces and considering instance interactions are crucial for robust GZSL.
  • The proposed techniques offer a promising direction for future research in zero-shot learning.