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

Observational Learning01:12

Observational Learning

804
Albert Bandura's observational learning, also known as imitation or modeling, occurs when a person observes and imitates another's behavior. It is a quicker process than operant conditioning. A well-known example is the Bobo doll study, where children who saw an adult acting aggressively towards the doll were more likely to act aggressively when left alone, compared to those who observed a nonaggressive adult. Many psychologists view observational learning as a form of latent learning...
804
Purposive Learning01:22

Purposive Learning

428
E. C. Tolman emphasized the purposiveness of behavior — the idea that much of our behavior is goal-directed. For instance, employees who aim for a promotion work diligently to meet their targets. Tolman argued that when classical conditioning and operant conditioning occur, the organism acquires certain expectations. In classical conditioning, a child might fear a dog because they expect it to bite. In operant conditioning, a person might consistently work overtime because they expect a...
428
Improving Translational Accuracy02:07

Improving Translational Accuracy

14.0K
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...
14.0K
Improving Translational Accuracy02:07

Improving Translational Accuracy

3.5K
3.5K
Associative Learning01:27

Associative Learning

1.2K
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...
1.2K
Introduction to Learning01:18

Introduction to Learning

912
Learning is the process of acquiring knowledge or skills through practice or experience, leading to long-lasting behavioral changes. This acquisition occurs through interaction with the environment and requires practice or experience. For instance, mastering a skill such as surfing requires considerable practice and experience, highlighting the essential role of repeated interactions with the environment in learning.
In contrast to learned behaviors, unlearned behaviors such as crying, sexual...
912

You might also read

Related Articles

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

Sort by
Same author

Assessing decarbonization strategies and industrial symbiosis in the chemical and waste-to-energy sector.

Journal of industrial ecology·2026
Same author

A continual learning framework with long-term and multiple short-term memory networks.

Neural networks : the official journal of the International Neural Network Society·2026
Same author

FISN: FInding Spatial Neighborhoods for Generalizable Novel View Synthesis.

IEEE transactions on visualization and computer graphics·2026
Same author

A Risk Prediction Model for Distal Aortic Negative Remodeling after TEVAR in Type B Aortic Dissection was Developed by Incorporating Novel Comprehensive Inflammatory Indices.

Annals of vascular surgery·2026
Same author

Model-Based Offline Reinforcement Learning With Adversarial Data Augmentation.

IEEE transactions on neural networks and learning systems·2025
Same author

Automated C. elegans behavior analysis via deep learning-based detection and tracking.

PLoS computational biology·2025
Same journal

Exploiting audio-visual modalities in videos: Object detection via multi-stage bilateral coupling network.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Reliability-aware modality completion with cross-modal distillation for federated learning with missing modalities.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

IGFD-Net: Illumination-guided frequency decoupling for polarization image fusion.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Multiple-Strategies dung beetle optimizer and its applications in engineering optimization and bankruptcy prediction.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Aggregating global-scale pixel-wise forgery cues within a graph.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Finite-Time intermittent control for secure synchronization of Neutral-Type stochastic delayed neural networks under aperiodic DoS attacks.

Neural networks : the official journal of the International Neural Network Society·2026
See all related articles

Related Experiment Video

Updated: Jan 11, 2026

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

1.0K

AMPL: An adaptive meta-prompt learner for few-shot image classification.

Zhiping Wu1, Lian Huai2, Tong Liu2

  • 1The State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, 210023, China.

Neural Networks : the Official Journal of the International Neural Network Society
|November 16, 2025
PubMed
Summary
This summary is machine-generated.

This study introduces the Adaptive Meta-Prompt Learner (AMPL) for few-shot image classification, improving recognition of novel classes with limited data. AMPL achieves state-of-the-art performance by adaptively learning visual prompts and enhancing token awareness.

Keywords:
Few-shot learningImage classificationMeta-Prompt learnerMeta-Visual-Prompts

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

9.9K

Related Experiment Videos

Last Updated: Jan 11, 2026

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

1.0K
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.9K

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Machine Learning

Background:

  • Few-shot image classification aims to recognize new classes using minimal labeled data.
  • Prompt-based learning, successful in NLP, has potential but underexplored applications in image classification.
  • Existing methods for few-shot image classification using prompts are often task-specific, limiting adaptability and increasing computational cost.

Purpose of the Study:

  • To introduce a novel framework, Adaptive Meta-Prompt Learner (AMPL), for effective few-shot image classification.
  • To address the limitations of task-specific prompt learning in terms of adaptability and computational efficiency.
  • To enhance the robustness and performance of few-shot image classification models across diverse tasks.

Main Methods:

  • Developed the Adaptive Meta-Prompt Learner (AMPL) framework to learn adaptive meta-visual-prompts for various few-shot tasks.
  • Utilized image patch features to generate dynamic visual prompts for rapid task adaptation.
  • Designed a Token-Awareness Enhancement Module to capture task-aware and vision-sensitive concepts through inter-token relationships.

Main Results:

  • Achieved new state-of-the-art classification performance on seven few-shot benchmark datasets.
  • Demonstrated significant improvements on the FC100 dataset, with absolute accuracy gains of 3.88% (1-shot) and 7.96% (5-shot) over hand-tuned prompt methods.
  • The proposed AMPL framework shows superior adaptability and robustness across different few-shot learning scenarios.

Conclusions:

  • The Adaptive Meta-Prompt Learner (AMPL) framework effectively enhances few-shot image classification by adaptively learning meta-visual-prompts.
  • The Token-Awareness Enhancement Module contributes to improved robustness and performance by leveraging inter-token relationships.
  • AMPL represents a significant advancement in prompt-based learning for computer vision tasks, offering improved accuracy and efficiency.