CVJun 21, 2021

Simple Distillation Baselines for Improving Small Self-supervised Models

arXiv:2106.11304v19 citationsHas Code
Originality Incremental advance
AI Analysis

This work addresses the performance gap for small self-supervised models in machine learning, though it is incremental as it builds on existing distillation techniques.

The paper tackles the problem of improving small self-supervised models, which lag behind large ones, by introducing simple distillation baselines called SimDis, resulting in a new state-of-the-art for offline distillation and competitive performance with low overhead for online distillation.

While large self-supervised models have rivalled the performance of their supervised counterparts, small models still struggle. In this report, we explore simple baselines for improving small self-supervised models via distillation, called SimDis. Specifically, we present an offline-distillation baseline, which establishes a new state-of-the-art, and an online-distillation baseline, which achieves similar performance with minimal computational overhead. We hope these baselines will provide useful experience for relevant future research. Code is available at: https://github.com/JindongGu/SimDis/

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes