动态加权知识蒸馏让卫星图像分类模型更轻更快，准确率超90%。
Semantic Knowledge Distillation for Onboard Satellite Earth Observation Image Classification
- 根据教师模型置信度动态分配知识权重，提升学习效率。
- 轻量学生模型ResNet8参数减少97.5%，推理速度提升63.5%。
- 适合资源受限的卫星端实时图像分类任务，部署友好。
本研究提出一种面向资源受限场景的高效地球观测（EO）图像分类动态加权知识蒸馏（KD）框架。采用EfficientViT和MobileViT作为教师模型，使轻量级学生模型（如ResNet8、ResNet16）在准确率、精确率和召回率上均超过90%，满足可靠分类任务的严格置信度要求。与传统静态权重方法不同，本框架基于教师模型置信度自适应调整知识来源优先级，实现动态优化。显著的是，ResNet8相较MobileViT实现参数减少97.5%、计算量（FLOPs）下降96.7%、功耗降低86.2%、推理速度提升63.5%。该框架有效平衡性能与资源开销，使轻量模型成为卫星端EO应用的理想选择。代码开源可复现。
原文摘要 · Abstract (English)
This study presents an innovative dynamic weighting knowledge distillation (KD) framework tailored for efficient Earth observation (EO) image classification (IC) in resource-constrained settings. Utilizing EfficientViT and MobileViT as teacher models, this framework enables lightweight student models, particularly ResNet8 and ResNet16, to surpass 90% in accuracy, precision, and recall, adhering to the stringent confidence thresholds necessary for reliable classification tasks. Unlike conventional KD methods that rely on static weight distribution, our adaptive weighting mechanism responds to each teacher model's confidence, allowing student models to prioritize more credible sources of knowledge dynamically. Remarkably, ResNet8 delivers substantial efficiency gains, achieving a 97.5% reduction in parameters, a 96.7% decrease in FLOPs, an 86.2% cut in power consumption, and a 63.5% increase in inference speed over MobileViT. This significant optimization of complexity and resource demands establishes ResNet8 as an optimal candidate for EO tasks, combining robust performance with feasibility in deployment. The confidence-based, adaptable KD approach underscores the potential of dynamic distillation strategies to yield high-performing, resource-efficient models tailored for satellite-based EO applications. The reproducible code is accessible on our GitHub repository.
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。