Self-supervised learning (SSL) is gaining attention for its ability to learn
effective representations with large amounts of unlabeled data.
Lightweight models can be distilled from larger self-supervised pre-trained
models using contrastive and consistency constraints.
Still, the different sizes of the projection heads make it challenging for
students to mimic the teacher's embedding accurately.
We propose \textsc{Retro}, which reuses the teacher's projection head for
students, and our experimental results demonstrate significant improvements
over the state-of-the-art on all lightweight models.
For instance, when training EfficientNet-B0 using ResNet-50/101/152 as
teachers, our approach improves the linear result on ImageNet to $66.9\%$,
$69.3\%$, and $69.8\%$, respectively, with significantly fewer parameters.

使用自监督学习 (SSL) 和对比约束以及一致性约束，从大量无标签数据中提取有效表示，并通过重用教师的投影头来改进轻量级模型，实验证明在所有轻量级模型上取得了显著的改进

Retro: 用于轻量级模型的自监督学习中的高效嵌入蒸馏的教师投影头的重复利用

\textsc{Retro}]{\textsc{Retro}: \underline{Re}using \underline{t}eacher  p\underline{ro}jection head for efficient embedding distillation on  Lightweight Models via Self-supervised Learning