用少样本学习实现高精度牛脸识别，解决传统标签易丢失问题。
CCoMAML: Efficient Cattle Identification Using Cooperative Model-Agnostic Meta-Learning
- 采用协作式元学习框架，仅需少量样本即可快速适应新牛只
- 在真实数据上达到98.46%和97.91%的F1分数
- 适合需要频繁更新模型的动态养牛场场景
牛只识别对高效畜牧管理至关重要，目前依赖射频识别（RFID）耳标，但易因丢失、损坏、篡改或外部攻击失效。作为替代方案，利用牛嘴部纹路进行生物特征识别类似人类指纹，展现出良好前景。深度学习已成功应用于该任务，但面临数据量少、采集中断及群体动态变化导致需频繁重训等问题。本文提出一种新型少样本学习框架CCoMAML，结合多头注意力特征融合（MHAFF）作为特征提取器，通过协作式模型无关元学习实现对新数据的高效适应，无需重新训练。在现有先进少样本学习方法对比实验中，所提方法在牛只识别任务上表现优异，分别取得98.46%和97.91%的F1分数。
原文摘要 · Abstract (English)
Cattle identification is critical for efficient livestock farming management, currently reliant on radio-frequency identification (RFID) ear tags. However, RFID-based systems are prone to failure due to loss, damage, tampering, and vulnerability to external attacks. As a robust alternative, biometric identification using cattle muzzle patterns similar to human fingerprints has emerged as a promising solution. Deep learning techniques have demonstrated success in leveraging these unique patterns for accurate identification. But deep learning models face significant challenges, including limited data availability, disruptions during data collection, and dynamic herd compositions that require frequent model retraining. To address these limitations, this paper proposes a novel few-shot learning framework for real-time cattle identification using Cooperative Model-Agnostic Meta-Learning (CCoMAML) with Multi-Head Attention Feature Fusion (MHAFF) as a feature extractor model. This model offers great model adaptability to new data through efficient learning from few data samples without retraining. The proposed approach has been rigorously evaluated against current state-of-the-art few-shot learning techniques applied in cattle identification. Comprehensive experimental results demonstrate that our proposed CCoMAML with MHAFF has superior cattle identification performance with 98.46% and 97.91% F1 scores.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。