Technology Category
Machine Learning: Active LearningComputer Vision: Video Understanding & Activity AnalysisSearch and Optimization: Learning to Search
Efficient Auto-Labeling of Large-Scale Poultry Datasets (ALPD) Using Semi-Supervised Models, Active Learning, and Prompt-then-Detect Approach
🤖 AI Summary
To address the time-consuming and non-scalable nature of manual annotation for poultry video data, this paper proposes ALPD—a novel automatic annotation framework integrating semi-supervised learning, active learning, and the Prompt-then-Detect paradigm. ALPD synergistically leverages multiple foundation models—including YOLOv8/v9, Grounding DINO, YOLO-World, and CLIP—to enable prompt-guided detection and intelligent sample selection. Evaluated on poultry behavior and breed recognition under low-data regimes, ALPD achieves 96.1% precision and 99.0% recall with YOLOv8s-ALPD; a hybrid YOLO-World variant attains 98.7% F1-score for breed detection and 84.5% F1-score for behavior detection; semi-supervised learning boosts behavior classification accuracy by 31%, while overall annotation efficiency improves by over 80%. This work establishes a scalable, efficient annotation infrastructure for AI-driven, large-scale poultry behavior monitoring and health assessment.
Technology Category
Application Category
📝 Abstract
The rapid growth of AI in poultry farming has highlighted the challenge of efficiently labeling large, diverse datasets. Manual annotation is time-consuming, making it impractical for modern systems that continuously generate data. This study explores semi-supervised auto-labeling methods, integrating active learning, and prompt-then-detect paradigm to develop an efficient framework for auto-labeling of large poultry datasets aimed at advancing AI-driven behavior and health monitoring. Viideo data were collected from broilers and laying hens housed at the University of Arkansas and the University of Georgia. The collected videos were converted into images, pre-processed, augmented, and labeled. Various machine learning models, including zero-shot models like Grounding DINO, YOLO-World, and CLIP, and supervised models like YOLO and Faster-RCNN, were utilized for broilers, hens, and behavior detection. The results showed that YOLOv8s-World and YOLOv9s performed better when compared performance metrics for broiler and hen detection under supervised learning, while among the semi-supervised model, YOLOv8s-ALPD achieved the highest precision (96.1%) and recall (99.0%) with an RMSE of 1.9. The hybrid YOLO-World model, incorporating the optimal YOLOv8s backbone, demonstrated the highest overall performance. It achieved a precision of 99.2%, recall of 99.4%, and an F1 score of 98.7% for breed detection, alongside a precision of 88.4%, recall of 83.1%, and an F1 score of 84.5% for individual behavior detection. Additionally, semi-supervised models showed significant improvements in behavior detection, achieving up to 31% improvement in precision and 16% in F1-score. The semi-supervised models with minimal active learning reduced annotation time by over 80% compared to full manual labeling. Moreover, integrating zero-shot models enhanced detection and behavior identification.
Problem
Research questions and friction points this paper is trying to address.
Automated Image Labeling
Poultry Farming
Artificial Intelligence
Innovation
Methods, ideas, or system contributions that make the work stand out.
Semi-supervised Learning
Active Learning
Transfer Learning
🔎 Similar Papers
No similar papers found.
