Performance of different student-teacher combinations using Tiny ImageNet dataset.

Our stochastic method consistently performs a lower carbon footprint than the tuned KD approach, keeping similar accuracy. ↑ (↓) means higher (lower) is better.我们所提出的随机方法始终较经调优的知识蒸馏（Knowledge Distillation，KD）方法拥有更低的碳足迹，同时保持相近的模型准确率。↑（↓）分别代表数值越高（越低）效果越好。