# Retro: Reusing teacher projection head for efficient embedding distillation on Lightweight Models via Self-supervised Learning

Source: [Retro: Reusing teacher projection head for efficient embedding distillation on Lightweight Models via Self-supervised Learning](<https://www.sota2.com/research/paper/68fa748c1e209131cea625fa>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T03:12:36.753Z

Authors: Khanh-Binh Nguyen, Chae Jung Park

Published: 2024-05-24T07:53:09.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2405.15311>)

[PDF](<https://arxiv.org/pdf/2405.15311.pdf>)