In the present article, an improved Knowledge Distillation (KD) framework has been proposed for efficient compression of deep convolutional neural networks for land-use image classification task. Motivated by the need to achieve competitive classification accuracy while reducing computational complexity, a teacher-student learning paradigm is adopted in which a VGG16 network transfers knowledge to a lightweight MobileNetV2 model. The proposed framework integrates hard supervision from ground truth labels with a soft supervision strategy that combines Kullback-Leibler divergence and Cosine Similarity losses. Experiments conducted on three land-use datasets show that the proposed KD-based method yields improved performance, and achieves an accuracy of 99.04%, outperforming both baseline student training and single-loss distillation approaches, while retaining substantial model compression.

翻译：本文提出了一种改进的知识蒸馏（KD）框架，用于高效压缩面向土地利用图像分类任务的深度卷积神经网络。为在降低计算复杂度的同时实现具有竞争力的分类精度，研究采用了教师-学生学习范式，其中VGG16网络将知识迁移至轻量级MobileNetV2模型。该框架整合了基于真实标签的硬监督策略，以及结合Kullback-Leibler散度与余弦相似度损失的软监督策略。在三个土地利用数据集上开展的实验表明，所提出的KD方法性能更优，在保持显著模型压缩效果的同时，取得了99.04%的准确率，优于基线学生训练模型及单一损失蒸馏方法。