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

Vision

Vision

Vision is the result of light being detected and transduced into neural signals by the retina of the eye. This information is then further analyzed and interpreted by the brain. First, light enters the front of the eye and is focused by the cornea and lens onto the retina—a thin sheet of neural tissue lining the back of the eye. Because of refraction through the convex lens of the eye, images are projected onto the retina upside-down and reversed.

You might also read

Related Articles

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

Sort by

Same author

A Data-Driven Spatiotemporal Risk Assessment Framework for Transformer Overload in Distributed Renewable Energy System.

Sensors (Basel, Switzerland)·2026

Same author

Causality-inspired crop pest recognition based on Decoupled Feature Learning.

Pest management science·2024

Same author

TSAF-Net: a rotated two-stage Cnaphalocrocis medinalis damage detection method based on anchor-free arbitrary-oriented proposal network.

Pest management science·2024

Same author

Identity-based controlled delegated outsourcing data integrity auditing scheme.

Scientific reports·2024

Same author

Optimization of Chemical Extraction Conditions of Dietary Fiber from <i>Cistanche deserticola</i> Residues and Its Structural Characteristics and Physicochemical and Functional Properties.

Molecules (Basel, Switzerland)·2023

Same author

Feature Refinement Method Based on the Two-Stage Detection Framework for Similar Pest Detection in the Field.

Insects·2023

Same journal

Effects of elevated CO<sub>2</sub> and temperature on cocklebur (Xanthium strumarium L.) and its herbicide response.

Pest management science·2026

Same journal

Kaolin particle films deter oviposition, impair early development of key soybean herbivore guilds, and enhance plant physiological resilience.

Pest management science·2026

Same journal

Pseudomonas chlororaphis IRHB3 suppresses Soybean mosaic virus by coordinating photosynthetic protection, ROS homeostasis and hormone-mediated immunity.

Pest management science·2026

Same journal

Hypogin-derived N-cinnamoylated peptide as a promising green fungicide against peanut southern blight caused by Sclerotium rolfsii.

Pest management science·2026

Same journal

Human activities and climatic factors drive decoupling effects of parasitoids-invasive agromyzid leafminers.

Pest management science·2026

Same journal

Dose-dependent efficacy of a novel dsRNA-based solution containing vadescana for Varroa destructor control.

Pest management science·2026

See all related articles

Search research articles

Related Experiment Video

Updated: May 6, 2026

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

PestCLIP: an incremental pest recognition framework based on a vision-language model.

Tao Hu^1,2, Xueheng Li^1,2, Ke Cao^1,2

¹Science Island Branch of Graduate School, University of Science and Technology of China, Hefei, China.

Pest Management Science

|February 20, 2026

Summary

This summary is machine-generated.

PestCLIP enhances agricultural pest recognition by using contrastive language-image pretraining (CLIP) to overcome catastrophic forgetting in class incremental learning. This AI framework improves adaptive pest management systems for dynamic environments.

Keywords:

Prediction Distribution Calibration class incremental learning incremental pest recognition vision‐language model

More Related Videos

Fully Automated Leg Tracking in Freely Moving Insects using Feature Learning Leg Segmentation and Tracking FLLIT

Fully Automated Leg Tracking in Freely Moving Insects using Feature Learning Leg Segmentation and Tracking FLLIT

Published on: April 23, 2020

A Bilingual Computational Workflow for Identifying Potential PLK1 Inhibitors in American Sign Language and English

A Bilingual Computational Workflow for Identifying Potential PLK1 Inhibitors in American Sign Language and English

Published on: April 3, 2026

Related Experiment Videos

Last Updated: May 6, 2026

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

Fully Automated Leg Tracking in Freely Moving Insects using Feature Learning Leg Segmentation and Tracking FLLIT

Fully Automated Leg Tracking in Freely Moving Insects using Feature Learning Leg Segmentation and Tracking FLLIT

Published on: April 23, 2020

A Bilingual Computational Workflow for Identifying Potential PLK1 Inhibitors in American Sign Language and English

A Bilingual Computational Workflow for Identifying Potential PLK1 Inhibitors in American Sign Language and English

Published on: April 3, 2026

Area of Science:

Agricultural Science
Artificial Intelligence
Computer Vision

Background:

Effective agricultural pest management is vital for food security and ecosystem health.
Current deep learning models struggle with incremental learning, leading to catastrophic forgetting of new pest species.
There is a need for adaptive AI frameworks for continuous and reliable pest recognition in dynamic agricultural settings.

Purpose of the Study:

To develop an AI framework for incremental pest recognition that addresses catastrophic forgetting.
To integrate advanced AI with ecological requirements for robust pest identification.
To enhance the adaptability and reliability of smart pest management systems.

Main Methods:

Proposed PestCLIP framework utilizing contrastive language-image pretraining (CLIP).
Employed dual-prompt tuning and a Concept Pool strategy to retain class features without extensive data replay.
Incorporated Prediction Distribution Calibration via incremental logit adjustment to mitigate bias.

Main Results:

PestCLIP achieved 97.50% accuracy on Li's dataset with a minimal 5.55% performance drop when learning new classes.
Demonstrated superior class incremental learning performance across agricultural (Li's, AgriInsect200, Farm Insect) and general (mini-ImageNet) datasets.
Visualizations confirmed effective preservation of class-specific concepts and reduced prediction bias.

Conclusions:

PestCLIP significantly outperforms existing methods in incremental pest recognition tasks.
The framework effectively preserves class concepts and calibrates prediction distributions, enhancing reliability.
PestCLIP represents a significant advancement for adaptive and intelligent pest management in agriculture.