用连续反向传播提升蜂蜜产地分类的增量学习效果
Class-Incremental Learning for Honey Botanical Origin Classification with Hyperspectral Images: A Study with Continual Backpropagation
- 将连续反向传播与增量学习结合，重置部分不活跃神经元以增强模型可塑性
- 在真实蜂蜜高光谱数据集上，多数增量学习方法准确率提升1%-7%
- 适合需要逐步添加新类别、避免遗忘的农业智能识别场景
蜂蜜是全球市场的重要商品，不同植物来源的蜂蜜具有多样风味和健康价值，因而市场价值各异。开发准确高效的产地溯源技术对保护消费者利益至关重要。然而一次性收集所有蜂蜜品种进行训练不现实，因此研究者采用类增量学习（CIL）应对该挑战。本研究在真实蜂蜜高光谱成像数据集上评估并比较了多种CIL算法，并提出一种新方法：通过结合持续反向传播（CB）算法改进CIL性能。CB通过重置部分使用频率较低的隐藏神经元，缓解模型遗忘问题。实验表明，该方法使多数CIL算法性能提升1%-7%。
原文摘要 · Abstract (English)
Honey is an important commodity in the global market. Honey types of different botanical origins provide diversified flavors and health benefits, thus having different market values. Developing accurate and effective botanical origin-distinguishing techniques is crucial to protect consumers' interests. However, it is impractical to collect all the varieties of honey products at once to train a model for botanical origin differentiation. Therefore, researchers developed class-incremental learning (CIL) techniques to address this challenge. This study examined and compared multiple CIL algorithms on a real-world honey hyperspectral imaging dataset. A novel technique is also proposed to improve the performance of class-incremental learning algorithms by combining with a continual backpropagation (CB) algorithm. The CB method addresses the issue of loss-of-plasticity by reinitializing a proportion of less-used hidden neurons to inject variability into neural networks. Experiments showed that CB improved the performance of most CIL methods by 1-7\%.
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。